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. 49853
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    ರೆ
    -0.08
     zombies
    -0.08
     addicts
    -0.08
     schizoph
    -0.07
     crunch
    -0.07
    ,同时
    -0.07
    热点
    -0.07
    ರು
    -0.07
    热门
    -0.07
     seedlings
    -0.07
    POSITIVE LOGITS
     tav
    0.09
     turb
    0.09
     towing
    0.08
    mä
    0.08
     Prü
    0.08
    -era
    0.08
     Moderne
    0.08
    -century
    0.08
     आधुनिक
    0.08
    -cache
    0.08
    Activations Density 0.032%

    No Known Activations