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. 113824
    Prev
    Next
    INDEX
    Explanations

    and

    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
     spouse
    -0.08
     Qaeda
    -0.08
    aille
    -0.08
     ró
    -0.08
     Drug
    -0.08
     Divorce
    -0.08
    中央値
    -0.08
     TOOL
    -0.08
     сторону
    -0.08
     spouses
    -0.08
    POSITIVE LOGITS
     cuidados
    0.08
     innovations
    0.08
     storytelling
    0.08
     cultural
    0.07
    创新
    0.07
     advocacy
    0.07
     تن
    0.07
     evolving
    0.07
     transformative
    0.07
     nurturing
    0.07
    Activations Density 0.070%

    No Known Activations