© 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. 23-RESID-POST-AA
    11. 51659
    Prev
    Next
    INDEX
    Explanations

    say "102"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inderella
    -0.08
     үнд
    -0.08
    ندی
    -0.08
     Heer
    -0.08
    ினிம
    -0.08
     sente
    -0.08
     delantero
    -0.07
    illard
    -0.07
     الإلكترونية
    -0.07
     [-]:
    -0.07
    POSITIVE LOGITS
    102
    0.17
    024
    0.08
    976
    0.08
    104
    0.08
    101
    0.08
    590
    0.07
     אותך
    0.07
    _photo
    0.07
    crumb
    0.07
    Ki
    0.07
    Activations Density 0.007%

    No Known Activations