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. 77443
    Prev
    Next
    INDEX
    Explanations

    3 or 8

    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
     artt
    -0.08
     pout
    -0.08
     Determine
    -0.07
     argumentative
    -0.07
     parall
    -0.07
     formen
    -0.07
     taku
    -0.07
    Tracer
    -0.07
    -headed
    -0.07
     isin
    -0.07
    POSITIVE LOGITS
     popular
    0.09
     популяр
    0.08
     Salad
    0.08
     salad
    0.08
     mushroom
    0.08
     настрой
    0.08
     recre
    0.08
     के
    0.07
     кө
    0.07
    ના
    0.07
    Activations Density 0.003%

    No Known Activations