© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7731
    Prev
    Next
    INDEX
    Explanations

    Standard/usual/scheduled

    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
    ás
    -0.09
     Taiwan
    -0.07
     Freder
    -0.07
    展示
    -0.07
     bele
    -0.07
     supervised
    -0.07
     aust
    -0.07
    ÁS
    -0.07
     quir
    -0.07
     dan
    -0.07
    POSITIVE LOGITS
     Verpflicht
    0.08
     Beginning
    0.08
     평균
    0.08
    .rating
    0.08
    ительность
    0.07
     rata
    0.07
    _method
    0.07
    _weapon
    0.07
    elligen
    0.07
     construed
    0.07
    Activations Density 0.025%

    No Known Activations