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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 74377
    Prev
    Next
    INDEX
    Explanations

    id

    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
     Burton
    -0.08
    BV
    -0.08
     произвед
    -0.07
     Brock
    -0.07
    重
    -0.07
    创造
    -0.07
     Ness
    -0.07
    驾驶
    -0.07
    Buen
    -0.07
     universe
    -0.07
    POSITIVE LOGITS
     senti
    0.08
     witnessing
    0.08
     ಸಂಪರ್ಕ
    0.08
     تز
    0.07
    akses
    0.07
    .analytics
    0.07
    whose
    0.07
     Favorites
    0.07
     Colored
    0.07
     شهد
    0.07
    Activations Density 0.003%

    No Known Activations