© 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. 69105
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     nhớ
    -0.08
     fud
    -0.07
    arf
    -0.07
     FAFSA
    -0.07
     FEL
    -0.07
     divisions
    -0.07
    fps
    -0.07
     жар
    -0.07
     кел
    -0.07
     физических
    -0.07
    POSITIVE LOGITS
     monot
    0.09
     Sharing
    0.09
     sharing
    0.09
     thus
    0.09
    Sharing
    0.08
    Nun
    0.08
     compartilhar
    0.08
    Serving
    0.08
     Thus
    0.08
    ינוק
    0.08
    Activations Density 0.037%

    No Known Activations