© 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. 24647
    Prev
    Next
    INDEX
    Explanations

    instructions/requirements

    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
     प्रतिभ
    -0.09
    ész
    -0.08
    -faire
    -0.08
     행사
    -0.08
     auprès
    -0.08
     terrains
    -0.07
     ವ್ಯಕ್ತ
    -0.07
     afford
    -0.07
     협
    -0.07
    Optimal
    -0.07
    POSITIVE LOGITS
    明确
    0.08
    年月
    0.08
     Mittelpunkt
    0.08
     uc
    0.08
    ാക്ക
    0.08
     maj
    0.07
     tin
    0.07
    ucar
    0.07
     bao
    0.07
     antal
    0.07
    Activations Density 0.017%

    No Known Activations