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

    Neuronpedia

    APICircuit 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. 53954
    Prev
    Next
    INDEX
    Explanations

    small areas

    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
    ural
    -0.08
     gowns
    -0.08
     notifications
    -0.08
     validates
    -0.08
    amit
    -0.08
    spl
    -0.07
     kinn
    -0.07
    gaand
    -0.07
    gbọ
    -0.07
     prek
    -0.07
    POSITIVE LOGITS
     regions
    0.16
     områder
    0.14
     Regions
    0.14
     പ്രദേശ
    0.13
     مناطق
    0.13
     regiones
    0.13
    regions
    0.13
    区域
    0.13
     areas
    0.13
     gebieden
    0.13
    Activations Density 0.048%

    No Known Activations