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. 130474
    Prev
    Next
    INDEX
    Explanations

    Chess pieces and strategy

    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
    Blur
    -0.08
     city
    -0.07
     applicable
    -0.07
    So
    -0.07
     blur
    -0.07
    orean
    -0.07
     platform
    -0.07
    hello
    -0.07
     "
    -0.07
     with
    -0.07
    POSITIVE LOGITS
     sacrificed
    0.10
    -loss
    0.10
     schweren
    0.10
    残局
    0.09
     اللعب
    0.09
     നഷ്ട
    0.09
     الثقيلة
    0.09
     الدفاع
    0.09
     LOST
    0.09
     رفع
    0.09
    Activations Density 0.004%

    No Known Activations