© 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. 8099
    Prev
    Next
    INDEX
    Explanations

    study analysis and interventions

    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
     Nih
    -0.08
     Tarn
    -0.08
     Grind
    -0.07
     Chim
    -0.07
     Gems
    -0.07
     trailer
    -0.07
    نامه
    -0.07
     damar
    -0.07
     chegada
    -0.07
    trusted
    -0.07
    POSITIVE LOGITS
     дәл
    0.08
     block
    0.08
    :block
    0.08
     effectief
    0.08
     interventions
    0.08
    类
    0.08
     platforms
    0.08
    otherapy
    0.08
    涉及
    0.08
    阻
    0.08
    Activations Density 0.015%

    No Known Activations