© 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. 7-RESID-POST-AA
    11. 1477
    Prev
    Next
    INDEX
    Explanations

    us

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Functional
    -0.08
    binding
    -0.08
     Binding
    -0.08
     Gér
    -0.08
     bind
    -0.08
     cradle
    -0.08
     Query
    -0.08
    വി
    -0.07
     binding
    -0.07
    _BIND
    -0.07
    POSITIVE LOGITS
     deception
    0.09
     stealth
    0.09
     premise
    0.09
     deceptive
    0.08
     deceit
    0.08
     sabot
    0.08
     escorts
    0.08
    َي
    0.08
     premises
    0.08
     covert
    0.08
    Activations Density 0.003%

    No Known Activations