© 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. 91466
    Prev
    Next
    INDEX
    Explanations

    .fill

    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
     hinged
    -0.08
     Routing
    -0.08
    has
    -0.08
     routed
    -0.07
    Routing
    -0.07
     Hik
    -0.07
    惊
    -0.07
    routing
    -0.07
    hik
    -0.07
     the
    -0.07
    POSITIVE LOGITS
     reclam
    0.09
     CGRect
    0.09
    :CGRect
    0.08
    ווען
    0.08
     QRect
    0.08
     pellets
    0.08
     imu
    0.08
     zašč
    0.08
    	Update
    0.08
     ដ
    0.08
    Activations Density 0.002%

    No Known Activations