Author

Lennart Stöpler

Heidelberg University

h-index 1 Homepage View on Semantic Scholar

We have 1 of 2 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Beyond a Bag of Features: Set-Level Instability in Sparse Autoencoders

It is found that SAE activation sets do not recover human category boundaries or within-category typicality more faithfully than dense embeddings or residual-stream states, but instead track model-internal similarity structure.

Nikolai Bolik, Lennart Stöpler, Artur Andrzejak · 0 citations