cs.LGNov 10, 2026

Massive Activations Confound Sparse Autoencoders

Authors: Nathan Delisle, Chenhao Tan

Organizations: University of Chicago

Abstract

Sparse autoencoders (SAEs) are commonly evaluated by variance explained and ablation damage. We show how massive activations undermine both evaluations, and propose a correction. Massive activations cause up to 99.9% of activation variance to lie along the first principal component (PC1). Because the PC1 component has no unique sparse decomposition, each SAE run rebuilds it from a different set of features. These features dominate importance rankings: an average of 47 of the 50 most important features are unmatched in a separate run, compared with about 27 of a random 50. A dictionary can also report 99.96% of variance explained while leaving 33% of the variance outside PC1 unexplained. We bypass PC1 by training the SAE on activations with PC1 removed, then adding PC1 to the reconstruction. In affected models, the top-50 feature sharing rate rises from 4-39.5% to 73-99.5%. At the same TopK sparsity, the resulting SAE degrades the model up to 44% less and reduces content reconstruction error by up to 33.9%.

Figures & tables

Appendix figures & tables63 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Jun 12, 2026

Decompose Sparsely Where You Should, Absorb Densely Where You Should No

Sparse autoencoders (SAEs) are typically trained to reconstruct the entire residual stream through a sparse dictionary, implicitly assuming that all activation content is amenable to sparse, monosemantic decomposition. We question this assumption and hypothesize that activations contain a low-rank, dense component that is computationally important to the model yet inherently unsuitable for sparse representation, which serves as a major source of the persistent dense latents widely observed in trained SAEs. To test this, we add a small rank-rr linear bottleneck in parallel with standard SAEs (BatchTopK and Matryoshka), allowing dense structure to be absorbed before sparse reconstruction. On Gemma-2-2B layer 12, a rank-24 bottleneck reduces dense latent count by up to 84% while improving sparse probing and targeted probe perturbation on both architectures at matched sparsity. The absorbed component is (i) structurally identifiable as the top principal components and outlier dimensions; (ii) causally necessary, with removing it raising next-token cross-entropy by 7.5×\times, far exceeding the 2.8×\times from removing the geometrically near-identical top-24 PCA directions; and (iii) redundantly encoded by sparse dictionaries, with ablating 787 maximally aligned sparse features raising cross-entropy by only 2.9×\times and ablating 2,048 topic-aligned features leaving MMLU topic classification virtually unchanged, whereas removing the scaffold drops it from 98.7% to chance. Together, our findings identify a compact, semantically informative and causally important component of residual stream activations (which we term a computational scaffold) that standard sparse dictionaries represent inefficiently, suggesting that the scope of sparsity-based interpretability methods warrants careful re-examination.
Aug 22, 2025

Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders

Sparse Autoencoders (SAEs) extract features from LLM internal activations, meant to correspond to interpretable concepts. A core SAE training hyperparameter is L0: how many SAE features should fire per token on average. Existing work compares SAE algorithms using sparsity-reconstruction tradeoff plots, implying L0 is a free parameter with no inherently correct value aside from its effect on reconstruction. In this work we study the effect of L0 on SAEs, and show that if L0 is not set correctly, the SAE fails to disentangle the underlying features of the LLM. If L0 is too low, the SAE will mix correlated features to improve reconstruction. If L0 is too high, the SAE finds degenerate solutions that also mix features. Further, we present a proxy metric that can help guide the search for the correct L0 for an SAE on a given training distribution. We show that our method finds the correct L0 in toy models and coincides with peak sparse probing performance in LLM SAEs. We find that most commonly used SAEs have an L0 that is too low. Our work shows that practitioners must set L0 correctly to train SAEs with monosemantic features.
May 29, 2026

On the Relationship Between Activation Outliers and Feature Death in Sparse Autoencoders

Sparse autoencoders (SAEs) decompose neural network activations into interpretable features, but many learned features never activate, a problem called feature death that wastes dictionary capacity and can reintroduce superposition. Death rates vary dramatically between models: near-zero on GPT-2, over 70% on AlphaFold3 with identical configurations. We find that dimension-level activation outliers (dimensions whose mean magnitude is large relative to per-token variation) cause this by shifting pre-activations at initialization based on each feature's alignment with the activation mean. Features anti-aligned with the mean receive permanently negative pre-activations and never fire. We formalize outlier severity as γ=∥μ∥/∥σ∥γ= \|μ\|/\|σ\|; it predicts initial death rates (Spearman ρ=0.89ρ= 0.89 for dead-by-TopK, 0.820.82 for dead-by-ReLU) across 454 model-layer combinations spanning language, vision, protein, and genomic models. Dead features can revive during training, but recovery requires the SAE bias to learn the activation mean, a process that is prohibitively slow at high γγ. Mean-centering (subtracting the activation mean) sidesteps this and eliminates outlier-induced death across all tested models, confirming the mechanism and providing a principled basis for when and why this preprocessing step is necessary.