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

    Neuronpedia

    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. 44680
    Prev
    Next
    INDEX
    Explanations

    dark mode

    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
     αί
    -0.07
     Kryptow
    -0.07
     wrench
    -0.07
     Mex
    -0.07
     Mechan
    -0.07
     between
    -0.07
     Democr
    -0.07
     민주
    -0.07
    Mex
    -0.07
     french
    -0.07
    POSITIVE LOGITS
    IFIED
    0.09
    uit
    0.08
    ائعة
    0.08
    ട്ട്
    0.08
    ‍या
    0.08
     delu
    0.08
     adaptations
    0.08
     flattering
    0.08
     kote
    0.07
    تي
    0.07
    Activations Density 0.001%

    No Known Activations