© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77814
    Prev
    Next
    INDEX
    Explanations

    calligraphy

    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
     pantry
    -0.08
    沿
    -0.08
     precaution
    -0.08
     cinemas
    -0.08
     Roche
    -0.07
    KEA
    -0.07
    福利
    -0.07
     #[
    -0.07
    措
    -0.07
     momentum
    -0.07
    POSITIVE LOGITS
    技巧
    0.11
     aficionados
    0.10
     woodworking
    0.10
     mastery
    0.10
     aesthetically
    0.10
     enthusiasts
    0.09
    高手
    0.09
     कला
    0.09
     impeccable
    0.09
     هنر
    0.09
    Activations Density 0.008%

    No Known Activations