© 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. 47155
    Prev
    Next
    INDEX
    Explanations

    scene

    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
    ads
    -0.09
     theatres
    -0.07
     Raceway
    -0.07
     전문가
    -0.07
     économiques
    -0.07
     Independence
    -0.07
     Lung
    -0.07
     statt
    -0.07
     конферен
    -0.07
     над
    -0.07
    POSITIVE LOGITS
    ையை
    0.08
    lius
    0.08
     largely
    0.08
    pherd
    0.07
     ndetse
    0.07
     reciente
    0.07
     kurzen
    0.07
    ם
    0.07
     downturn
    0.07
     Axios
    0.07
    Activations Density 0.276%

    No Known Activations