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. 114075
    Prev
    Next
    INDEX
    Explanations

    Architectural design elements

    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
     barbar
    -0.08
     champion
    -0.08
    upplier
    -0.08
     চোখ
    -0.08
    音
    -0.07
     منت
    -0.07
     Burundi
    -0.07
    整数
    -0.07
     FBI
    -0.07
     lucky
    -0.07
    POSITIVE LOGITS
    ></
    0.08
     protr
    0.08
     retract
    0.08
    Inset
    0.08
    Margin
    0.08
    ilt
    0.08
     Parsing
    0.08
     margin
    0.08
     усил
    0.08
    [,]
    0.08
    Activations Density 0.004%

    No Known Activations