© 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. 23-RESID-POST-AA
    11. 6138
    Prev
    Next
    INDEX
    Explanations

    fetal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cl
    -0.08
     Se
    -0.08
    (cl
    -0.08
     Cl
    -0.08
    ,se
    -0.08
    sealed
    -0.08
    se
    -0.08
    Se
    -0.08
     sealed
    -0.08
    -cl
    -0.08
    POSITIVE LOGITS
     kicks
    0.13
     kicking
    0.12
     kick
    0.12
     movements
    0.11
     präsent
    0.10
     kicked
    0.10
     apresentação
    0.10
     Kick
    0.10
     apresentar
    0.10
     apresentações
    0.09
    Activations Density 0.006%

    No Known Activations