© 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. 592
    Prev
    Next
    INDEX
    Explanations

    analysis

    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
     Exhaust
    -0.09
     painstaking
    -0.09
     intimacy
    -0.08
     Ultimately
    -0.08
     meticulous
    -0.08
     Detailed
    -0.08
    成为
    -0.07
     Become
    -0.07
     Extensive
    -0.07
     intimate
    -0.07
    POSITIVE LOGITS
     действия
    0.09
     صغيرة
    0.09
     చిన్న
    0.08
     صغير
    0.08
     commas
    0.08
     قليلة
    0.08
     ação
    0.08
    0.08
     beperkt
    0.08
     acciones
    0.08
    Activations Density 0.038%
    No Known Activations