© 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. 129376
    Prev
    Next
    INDEX
    Explanations

    all

    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
     dell
    -0.08
     Boston
    -0.07
     యొక్క
    -0.07
     వల్ల
    -0.07
    illo
    -0.07
    ata
    -0.07
     Citizen
    -0.07
    事项
    -0.07
     Rim
    -0.07
    Boston
    -0.07
    POSITIVE LOGITS
     imaginable
    0.09
     файлов
    0.09
    ческих
    0.08
     απ
    0.08
     avali
    0.08
    ческие
    0.08
     armen
    0.08
     çeşit
    0.08
    škai
    0.08
     Ain
    0.08
    Activations Density 0.001%

    No Known Activations