© 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. 48093
    Prev
    Next
    INDEX
    Explanations

    say threshold

    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
     hinten
    -0.07
     emoties
    -0.07
     Jai
    -0.07
     Información
    -0.07
     rie
    -0.07
     accessories
    -0.07
     Movimento
    -0.07
    ندس
    -0.07
    ิล
    -0.07
    uedo
    -0.06
    POSITIVE LOGITS
     threshold
    0.67
    threshold
    0.61
    Threshold
    0.61
    _threshold
    0.61
     Threshold
    0.59
     thresholds
    0.58
    .threshold
    0.57
    _THRESHOLD
    0.56
     seuil
    0.51
    _thresh
    0.47
    Activations Density 0.285%

    No Known Activations