Safety researcher

Joshua Batson

Co-authored 'Towards Monosemanticity,' using sparse autoencoders to decompose transformer activations into interpretable features.

Works in the archive (1)

“Lead” marks the first-listed author — a byline fact, not a measure of influence; co-authorship is shown as recorded.

Co-authors in the archive

Trenton Bricken, Adly Templeton, Chris Olah