Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 120225
    Prev
    Next
    INDEX
    Explanations

    sensors

    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
     gospodar
    -0.09
     dominance
    -0.08
     સંપ
    -0.08
     domina
    -0.08
     dominates
    -0.08
     acronym
    -0.08
     અક
    -0.08
     rehab
    -0.08
    .help
    -0.08
    יפול
    -0.07
    POSITIVE LOGITS
    检测
    0.12
     detecting
    0.11
     sensing
    0.11
    监
    0.10
     monitoring
    0.10
     telemetry
    0.10
    反馈
    0.09
     Sensors
    0.09
    Monitoring
    0.09
     Monitoring
    0.09
    Activations Density 0.018%

    No Known Activations