© 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. 65460
    Prev
    Next
    INDEX
    Explanations

    neurotransmitters

    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
     estrutur
    -0.09
    _RS
    -0.08
     decades
    -0.08
    STRUCT
    -0.08
     Ew
    -0.08
    IEWS
    -0.08
    _SUPPORTED
    -0.07
     Christianity
    -0.07
    Structure
    -0.07
     Structure
    -0.07
    POSITIVE LOGITS
    த்தின்
    0.09
     zadovolj
    0.09
     bienestar
    0.09
    幸福
    0.08
     obedience
    0.08
     joyful
    0.08
     সুখ
    0.08
     desserts
    0.08
     wellness
    0.08
     onboarding
    0.08
    Activations Density 0.003%

    No Known Activations