© 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. 3-RESID-POST-AA
    11. 2724
    Prev
    Next
    INDEX
    Explanations

    &

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     �
    -0.09
    )e
    -0.08
     circumvent
    -0.08
    �
    -0.07
     Nud
    -0.07
    서를
    -0.07
     Lamar
    -0.07
     sedation
    -0.07
     exper
    -0.07
    eness
    -0.07
    POSITIVE LOGITS
     GPIO
    0.08
    وغ
    0.08
    Ty
    0.08
    celer
    0.07
    ceb
    0.07
    轴
    0.07
    Nothing
    0.07
    сөн
    0.07
     Ty
    0.07
    owl
    0.07
    Activations Density 0.003%

    No Known Activations