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. 54177
    Prev
    Next
    INDEX
    Explanations

    tides and gravity

    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
     로그
    -0.08
    ログ
    -0.08
     SMT
    -0.08
     Shutdown
    -0.08
     reused
    -0.08
    로그
    -0.07
     frying
    -0.07
     Intervention
    -0.07
    ILog
    -0.07
    명을
    -0.07
    POSITIVE LOGITS
     нагруз
    0.09
     शक्त
    0.08
    -We
    0.08
     earthquakes
    0.08
     చంద్ర
    0.08
     tsunami
    0.08
     כוח
    0.08
     Confederate
    0.08
     Earth's
    0.07
    ēc
    0.07
    Activations Density 0.003%

    No Known Activations