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. 77518
    Prev
    Next
    INDEX
    Explanations

    Tired of

    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
     vmax
    -0.08
     glacier
    -0.08
     Secrets
    -0.08
    মূল
    -0.08
    ооп
    -0.08
     Champions
    -0.07
    .closest
    -0.07
    确认
    -0.07
    最佳
    -0.07
    manız
    -0.07
    POSITIVE LOGITS
     tired
    0.09
     frustration
    0.09
    疲
    0.08
     rồi
    0.08
     frustrations
    0.08
     nag
    0.08
     cesse
    0.08
     bỏ
    0.08
     fatigue
    0.08
     चुके
    0.08
    Activations Density 0.019%

    No Known Activations