© 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. 50700
    Prev
    Next
    INDEX
    Explanations

    [

    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
    ическом
    -0.08
     enclosed
    -0.08
    ிகள
    -0.08
    ીઓને
    -0.08
    īja
    -0.08
    otta
    -0.08
    angunan
    -0.08
    ీల
    -0.08
    ியின்
    -0.08
    isements
    -0.08
    POSITIVE LOGITS
     Мак
    0.08
    ឺ
    0.08
    ]\
    0.08
    موضوع
    0.07
    detail
    0.07
     heti
    0.07
     apropi
    0.07
     ಮೂ
    0.07
     Tenho
    0.07
    适
    0.07
    Activations Density 0.004%

    No Known Activations