© 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. 6231
    Prev
    Next
    INDEX
    Explanations

    �

    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
     Б
    -0.08
     ம
    -0.08
    .P
    -0.07
     PDT
    -0.07
     Wh
    -0.07
     πλευ
    -0.07
     wc
    -0.07
     プ
    -0.07
     特
    -0.07
    特
    -0.07
    POSITIVE LOGITS
     đau
    0.09
    textarea
    0.09
    goog
    0.08
    acciones
    0.08
    ज्ज
    0.08
    accion
    0.08
     emergencies
    0.08
    痛
    0.08
    laugh
    0.08
     vandal
    0.08
    Activations Density 0.000%

    No Known Activations