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. 90808
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    inda
    -0.08
    Discount
    -0.07
    .gu
    -0.07
    ाचा
    -0.07
    .easy
    -0.07
    ama
    -0.07
    hello
    -0.07
    .acquire
    -0.07
     gran
    -0.07
    -0.07
    POSITIVE LOGITS
     ஆகிய
    0.11
     എന്നിവ
    0.08
    ។↵↵
    0.08
     unor
    0.08
     };↵//
    0.08
     ।
    0.07
     ।↵
    0.07
    ↵    ↵    ↵
    0.07
     ।↵↵
    0.07
     pomemb
    0.07
    Activations Density 0.192%

    No Known Activations