© 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. 111439
    Prev
    Next
    INDEX
    Explanations

    normal

    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
     fruition
    -0.08
     premises
    -0.08
     Mavericks
    -0.07
     sap
    -0.07
    semicolon
    -0.07
     exhaustive
    -0.07
     seek
    -0.07
    _sigma
    -0.07
     доступны
    -0.07
    sigma
    -0.07
    POSITIVE LOGITS
     omhoog
    0.08
    ाई
    0.08
    .Direction
    0.08
    太阳
    0.08
    pendicular
    0.08
    richtung
    0.07
     बोल
    0.07
     punched
    0.07
     ripping
    0.07
     Rival
    0.07
    Activations Density 0.003%

    No Known Activations