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. 11819
    Prev
    Next
    INDEX
    Explanations

    common English words

    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
    olda
    -0.07
     Elliott
    -0.07
    bands
    -0.07
    .ends
    -0.07
    gah
    -0.07
     próximas
    -0.07
     constituent
    -0.07
     Vater
    -0.07
     ग्रह
    -0.07
    [state
    -0.07
    POSITIVE LOGITS
    দের
    0.13
    *innen
    0.12
    :innen
    0.12
     যারা
    0.11
    에게
    0.11
     tərəfindən
    0.10
     tomonidan
    0.10
    রা
    0.10
     którzy
    0.10
    들에게
    0.10
    Activations Density 0.421%

    No Known Activations