Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56223
    Prev
    Next
    INDEX
    Explanations

    Stewart

    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
     Gestaltung
    -0.08
    ULATION
    -0.08
    ,name
    -0.08
    UL
    -0.08
     sais
    -0.07
    ulating
    -0.07
     disadvantaged
    -0.07
     Issues
    -0.07
     blur
    -0.07
    振
    -0.07
    POSITIVE LOGITS
    казы
    0.08
     vervo
    0.08
    каз
    0.08
     тканей
    0.08
     tassa
    0.08
    каж
    0.08
    эр
    0.08
    roep
    0.08
     eléctrica
    0.08
     Как
    0.08
    Activations Density 0.000%

    No Known Activations