© 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 EvalsExportsinterp-engineNEWAPI 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. 110373
    Prev
    Next
    INDEX
    Explanations

    Cleaning/Trash Removal

    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
    -0.08
     horns
    -0.07
     horn
    -0.07
     Sergio
    -0.07
    ī
    -0.07
    тори
    -0.07
    day
    -0.06
     לתת
    -0.06
    ać
    -0.06
     Fran
    -0.06
    POSITIVE LOGITS
     julka
    0.09
     производится
    0.09
     publiée
    0.08
     жария
    0.08
     адбы
    0.08
    掲載
    0.08
     cougar
    0.08
     muna
    0.08
     Автор
    0.08
    mür
    0.08
    Activations Density 0.006%
    No Known Activations