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. 9060
    Prev
    Next
    INDEX
    Explanations

    well

    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
     manageable
    -0.09
    ping
    -0.08
    机制
    -0.07
    inicio
    -0.07
     Level
    -0.07
     compleet
    -0.07
     geïnteresse
    -0.07
     kuat
    -0.07
    展开
    -0.07
     Start
    -0.07
    POSITIVE LOGITS
    ərbaycan
    0.09
    ဘာ
    0.09
     Sund
    0.09
    translation
    0.09
    _proto
    0.08
     중국
    0.08
     UCLA
    0.08
    睛
    0.08
     Burkina
    0.08
     Redmi
    0.08
    Activations Density 0.014%

    No Known Activations