© 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. 19-RESID-POST-AA
    11. 103134
    Prev
    Next
    INDEX
    Explanations

    Attack, defense and speed

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aylor
    -0.09
    piro
    -0.08
     Leta
    -0.08
    zinha
    -0.07
    สัมพันธ์
    -0.07
     conjuntamente
    -0.07
    _merge
    -0.07
    jectory
    -0.07
    uille
    -0.07
     Combining
    -0.07
    POSITIVE LOGITS
     velocidad
    0.12
    .speed
    0.11
    .Speed
    0.11
     defensa
    0.11
     velocidade
    0.10
    .DEF
    0.10
     vitesse
    0.10
     armor
    0.10
     ವೇ
    0.09
     defense
    0.09
    Activations Density 0.003%

    No Known Activations