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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43366
    Prev
    Next
    INDEX
    Explanations

    umi

    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
     acknowledging
    -0.08
     acknowledge
    -0.08
     Ergän
    -0.08
    唱
    -0.08
    -headed
    -0.08
     ergänzt
    -0.08
    يمان
    -0.08
    _VALIDATE
    -0.08
     الأربع
    -0.07
     마사지
    -0.07
    POSITIVE LOGITS
    amo
    0.07
     mond
    0.07
     GN
    0.07
    .ship
    0.07
     IND
    0.07
    Qui
    0.07
     ಶು
    0.07
    REB
    0.07
    Integer
    0.07
     intégré
    0.07
    Activations Density 0.002%

    No Known Activations