© 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. 47827
    Prev
    Next
    INDEX
    Explanations

    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
    .we
    -0.08
     uncontrolled
    -0.07
     Hollywood
    -0.07
     synd
    -0.07
     subtype
    -0.07
     overhead
    -0.07
     kase
    -0.07
     silo
    -0.07
    .control
    -0.07
    raš
    -0.07
    POSITIVE LOGITS
     كلام
    0.09
     práctico
    0.09
     autobi
    0.09
     Principles
    0.09
     Philosophy
    0.08
    ութիւն
    0.08
     Appendix
    0.08
     ابن
    0.08
    (stream
    0.08
     гэж
    0.08
    Activations Density 0.023%

    No Known Activations