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. 61045
    Prev
    Next
    INDEX
    Explanations

    backtick

    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
     scrap
    -0.09
     tipped
    -0.08
    讨
    -0.08
    /FM
    -0.08
     LY
    -0.08
     gereken
    -0.07
     recommand
    -0.07
     slightest
    -0.07
     preis
    -0.07
    /or
    -0.07
    POSITIVE LOGITS
     Далее
    0.10
     এরপর
    0.09
     Затем
    0.09
    ervolgens
    0.09
     وبعد
    0.09
     followed
    0.08
    дел
    0.08
     ಇಲ್ಲಿ
    0.08
     लोक
    0.08
     Vervolgens
    0.08
    Activations Density 0.037%

    No Known Activations