© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 19531
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     digs
    -0.08
     donc
    -0.08
     ايضا
    -0.08
     proposals
    -0.08
     appointments
    -0.08
     assists
    -0.08
     contenders
    -0.08
     quindi
    -0.08
     probablement
    -0.08
     nominations
    -0.07
    POSITIVE LOGITS
    ="
    0.09
    ="[
    0.08
     Uku
    0.08
    ="<?=
    0.08
    'idée
    0.08
    […
    0.08
    ?↵↵
    0.08
     Hoʻ
    0.08
    [
    0.08
    ="\
    0.08
    Activations Density 0.008%

    No Known Activations