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. 77338
    Prev
    Next
    INDEX
    Explanations

    proton

    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
     Outfit
    -0.09
     приз
    -0.09
     fflush
    -0.08
     outfit
    -0.08
     Outcome
    -0.08
    printf
    -0.07
     Outcomes
    -0.07
    scanf
    -0.07
    älj
    -0.07
    ителя
    -0.07
    POSITIVE LOGITS
     tension
    0.08
    焼
    0.07
     Ի
    0.07
    lles
    0.07
     Hulu
    0.07
     ھ
    0.07
     streamer
    0.07
    γμα
    0.07
     fim
    0.07
    ゲ
    0.07
    Activations Density 0.001%

    No Known Activations