Cross-Family Transfer of Sparse Autoencoder Features Is Real but Readout-Dependent: A Preregistered Reanalysis

Do sparse autoencoder (SAE) features matched between language models of different families act on the second model the way that model's own feature does? A common shortcut maps a source decoder direction into the target residual stream, adds it, and reads the target SAE encoder at the same tensor. We show that this readout is a first-order encoder projection (Spearman 0.97 with the encoder-row projection in a GPT-2 to Pythia-70m pilot), that the pilot's "130 times random" headline rested on a near-zero denominator, and that its negative Procrustes R² (−1.15) was a scale artifact (0.49 with a fitted scale). We then run a preregistered study on GPT-2 small, Pythia-70m and Qwen3-1.7B-Base with public SAEs, tokenizer-independent word-level matching against a multiple-comparisons-aware null, and readouts that pass through the target model: the downstream SAE code and the next-token distribution. Transfer exceeds mismatched and Gaussian nulls in all four directed pairs (all 24 primary tests survive Holm correction). But raw downstream readouts also credit large nonspecific effects: a mismatched mapped direction reaches τL between 0.46 and 0.64 of the native effect at the preregistered magnitude. Net of that null, transfer is 0.17 to 0.42 of native for the downstream SAE readout. Contrary to our preregistered expectation, the encoder readout does not overstate transfer; it is below the raw causal readouts in every pair. Transfer is predicted mainly by the cosine between mapped and native decoder directions (pooled ρ = 0.63), and the pilot's match-correlation predictor does not replicate.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-17
DOI
https://doi.org/10.5281/zenodo.24326153
Primary Topic
Topic Modeling
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Cross-Family Transfer of Sparse Autoencoder Features Is Real but Readout-Dependent: A Preregistered Reanalysis

Sharven Rane
Zenodo (CERN European Organization for Nuclear Research)
Topic Modeling
preprint

Cross-Family Transfer of Sparse Autoencoder Features Is Real but Readout-Dependent: A Preregistered Reanalysis

Sharven Rane
preprint en

Abstract

Do sparse autoencoder (SAE) features matched between language models of different families act on the second model the way that model's own feature does? A common shortcut maps a source decoder direction into the target residual stream, adds it, and reads the target SAE encoder at the same tensor. We show that this readout is a first-order encoder projection (Spearman 0.97 with the encoder-row projection in a GPT-2 to Pythia-70m pilot), that the pilot's "130 times random" headline rested on a near-zero denominator, and that its negative Procrustes R² (−1.15) was a scale artifact (0.49 with a fitted scale). We then run a preregistered study on GPT-2 small, Pythia-70m and Qwen3-1.7B-Base with public SAEs, tokenizer-independent word-level matching against a multiple-comparisons-aware null, and readouts that pass through the target model: the downstream SAE code and the next-token distribution. Transfer exceeds mismatched and Gaussian nulls in all four directed pairs (all 24 primary tests survive Holm correction). But raw downstream readouts also credit large nonspecific effects: a mismatched mapped direction reaches τL between 0.46 and 0.64 of the native effect at the preregistered magnitude. Net of that null, transfer is 0.17 to 0.42 of native for the downstream SAE readout. Contrary to our preregistered expectation, the encoder readout does not overstate transfer; it is below the raw causal readouts in every pair. Transfer is predicted mainly by the cosine between mapped and native decoder directions (pooled ρ = 0.63), and the pilot's match-correlation predictor does not replicate.

Zenodo (CERN European Organization for Nuclear Research)
Topic Modeling
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon