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. 76072
    Prev
    Next
    INDEX
    Explanations

    events and festivals

    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
     horr
    -0.07
     Теперь
    -0.07
     incorrectly
    -0.07
    _ts
    -0.07
     Rechn
    -0.07
    _std
    -0.07
    .W
    -0.07
     metri
    -0.07
     większo
    -0.07
     kg
    -0.07
    POSITIVE LOGITS
    专题
    0.11
     keynote
    0.09
    Saturday
    0.09
    Gov
    0.09
     surveyed
    0.09
    GLE
    0.09
    embrance
    0.08
    Wednesday
    0.08
    Presenter
    0.08
     citoy
    0.08
    Activations Density 0.272%

    No Known Activations