© 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. 11-RESID-POST-AA
    11. 70291
    Prev
    Next
    INDEX
    Explanations

    business and technical topics

    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
     card
    -0.07
     subtree
    -0.07
     ration
    -0.07
     CARD
    -0.07
     cas
    -0.07
     τη
    -0.07
     diet
    -0.07
     lat
    -0.07
     eliminar
    -0.07
     repeating
    -0.06
    POSITIVE LOGITS
     gue
    0.08
     Enh
    0.08
    Stan
    0.08
    .Es
    0.08
     unbel
    0.08
     Ellen
    0.07
    -Ste
    0.07
    -----------------------------------------------------------------------------↵
    0.07
     Vancouver
    0.07
    (Not
    0.07
    Activations Density 0.192%

    No Known Activations