© 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. 69875
    Prev
    Next
    INDEX
    Explanations

    mathematical problems

    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
     ਚ
    -0.08
     prevention
    -0.07
     Prevention
    -0.07
    运
    -0.07
     Heng
    -0.07
    -0.07
    PF
    -0.07
     Aspir
    -0.06
     COLORS
    -0.06
    運
    -0.06
    POSITIVE LOGITS
     réellement
    0.09
     khona
    0.09
     daadwerkelijk
    0.09
    (es
    0.09
     flest
    0.08
     truly
    0.08
    ่อย
    0.08
     capable
    0.08
     realmente
    0.08
     workable
    0.08
    Activations Density 0.034%
    No Known Activations