© 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. 11-RESID-POST-AA
    11. 68273
    Prev
    Next
    INDEX
    Explanations

    math operations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     консульт
    -0.10
     оку
    -0.10
     спортсмен
    -0.09
     консульта
    -0.09
     спортив
    -0.09
     پرو
    -0.09
     советы
    -0.08
     کامل
    -0.08
    องค์กร
    -0.08
     оплач
    -0.08
    POSITIVE LOGITS
     final
    0.08
    526
    0.07
    82
    0.07
    tis
    0.07
    521
    0.07
    0.07
    de
    0.07
    _final
    0.07
     Final
    0.07
     finais
    0.07
    Activations Density 0.006%
    No Known Activations