© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 47129
    Prev
    Next
    INDEX
    Explanations

    medicine/science

    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
    det
    -0.09
     perspectives
    -0.08
     principes
    -0.08
     projections
    -0.08
     abol
    -0.07
    nap
    -0.07
     journeys
    -0.07
    iran
    -0.07
    .scope
    -0.07
    Soul
    -0.07
    POSITIVE LOGITS
    曲
    0.08
     repairs
    0.08
    骑
    0.08
     horseback
    0.08
    炮
    0.08
     repaired
    0.08
    -centered
    0.08
     يعد
    0.08
     થઈ
    0.08
     Bug
    0.08
    Activations Density 0.008%

    No Known Activations