Pith. sign in

ReLU or TopK θ= (W enc, Wdec,b enc,b dec)parameter tuple of an SAE Θclass of SAEs under consideration Data generating process V= (v 1,

11 A Notation Symbol Meaning Dimensions ddimension of the ambient activation space mSAE width (number of latent coordinates) nnumber of ground-truth concepts in the DGP KTopK sparsity budget, when applicable Sparse autoencoder x∈R d input a · 2006

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

The Rate-Distortion-Polysemanticity Tradeoff in SAEs

cs.LG · 2026-05-14 · unverdicted · novelty 6.0

SAEs exhibit a rate-distortion-polysemanticity tradeoff where monosemanticity increases rate and distortion, with optimal polysemanticity set by feature co-occurrence probabilities in the data.

citing papers explorer

Showing 1 of 1 citing paper.

  • The Rate-Distortion-Polysemanticity Tradeoff in SAEs cs.LG · 2026-05-14 · unverdicted · none · ref 18

    SAEs exhibit a rate-distortion-polysemanticity tradeoff where monosemanticity increases rate and distortion, with optimal polysemanticity set by feature co-occurrence probabilities in the data.