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. 77357
    Prev
    Next
    INDEX
    Explanations

    browse internet

    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
    Handlers
    -0.08
     desn
    -0.08
     combustible
    -0.07
     ENTRY
    -0.07
    _______________
    -0.07
     배
    -0.07
     Johnson
    -0.07
     своей
    -0.07
    яду
    -0.07
     steer
    -0.07
    POSITIVE LOGITS
     externas
    0.09
    互联网
    0.08
     external
    0.08
     internet
    0.08
     externos
    0.08
    访问
    0.08
    /story
    0.08
     externo
    0.08
     ഔ
    0.08
     endpoint
    0.08
    Activations Density 0.007%

    No Known Activations