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. 98941
    Prev
    Next
    INDEX
    Explanations

    copyright/royalties

    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
    jum
    -0.08
     Abschluss
    -0.08
     Challenge
    -0.07
    徒
    -0.07
     Guide
    -0.07
     Tahun
    -0.07
     obe
    -0.07
     પૂર્ણ
    -0.07
     Punch
    -0.07
     Без
    -0.07
    POSITIVE LOGITS
     royalties
    0.12
    传播
    0.10
     unauthorized
    0.10
     auctions
    0.09
     monetize
    0.09
     owners
    0.09
    出演
    0.09
     Unauthorized
    0.09
     monet
    0.09
     თვალ
    0.09
    Activations Density 0.038%

    No Known Activations