© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68126
    Prev
    Next
    INDEX
    Explanations

    enhancement or expansion

    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
     సభ
    -0.08
    .dt
    -0.08
     overseas
    -0.08
     preceded
    -0.08
     zamanda
    -0.08
     அ
    -0.08
     famosos
    -0.08
    (图
    -0.08
     existen
    -0.08
    -0.07
    POSITIVE LOGITS
     synerg
    0.13
     comprehensive
    0.13
     Comprehensive
    0.10
    全面
    0.10
     synergy
    0.10
     versatility
    0.10
     संयुक्त
    0.10
     richer
    0.09
     richness
    0.09
    -rounded
    0.09
    Activations Density 0.048%
    No Known Activations