© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110180
    Prev
    Next
    INDEX
    Explanations

    ES

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    station
    -0.08
     Burt
    -0.08
     ragaz
    -0.08
     cz
    -0.08
     Morr
    -0.07
     Von
    -0.07
     nešto
    -0.07
    étr
    -0.07
    amation
    -0.07
     garçon
    -0.07
    POSITIVE LOGITS
     fatty
    0.08
    バック
    0.08
    Drawable
    0.08
    684
    0.08
     aiding
    0.08
    (help
    0.07
    Scrollable
    0.07
     flood
    0.07
     punct
    0.07
    _fd
    0.07
    Activations Density 0.020%

    No Known Activations