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

    Neuronpedia

    Jacobian LensNEW
    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. 113674
    Prev
    Next
    INDEX
    Explanations

    sleep

    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
     Sothe
    -0.10
     explosion
    -0.08
     diamant
    -0.08
     priced
    -0.08
    Explosion
    -0.08
     beschäd
    -0.08
     embroidered
    -0.08
     Explosion
    -0.08
    CRUD
    -0.08
    实力
    -0.08
    POSITIVE LOGITS
     sleep
    0.17
     النوم
    0.17
    睡
    0.16
    _sleep
    0.16
     Sleep
    0.16
    Sleep
    0.15
     noct
    0.15
     slaap
    0.15
     sauna
    0.14
     физи
    0.14
    Activations Density 0.067%

    No Known Activations