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. 43783
    Prev
    Next
    INDEX
    Explanations

    thunder

    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
    imd
    -0.08
     dereg
    -0.08
     unmarried
    -0.07
     nako
    -0.07
     znal
    -0.07
     Pra
    -0.07
    undet
    -0.07
     unwind
    -0.07
    agot
    -0.07
     ufa
    -0.07
    POSITIVE LOGITS
    bolt
    0.10
    ous
    0.10
    ously
    0.09
     carbide
    0.08
    峰
    0.08
    iose
    0.08
    Bolt
    0.08
    thest
    0.07
    烈
    0.07
    uous
    0.07
    Activations Density 0.003%

    No Known Activations