© 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. 15-RESID-POST-AA
    11. 16306
    Prev
    Next
    INDEX
    Explanations

    say "what"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     även
    -0.09
     Het
    -0.07
    Other
    -0.07
    Distinct
    -0.07
     core
    -0.07
     Other
    -0.07
    -0.07
    Het
    -0.07
     linkage
    -0.06
     Duk
    -0.06
    POSITIVE LOGITS
     what
    0.23
     શું
    0.23
     무엇
    0.23
     क्या
    0.23
    什么
    0.21
     ماذا
    0.21
     എന്ത
    0.21
     ఏమ
    0.20
    what
    0.20
    What
    0.20
    Activations Density 0.050%
    No Known Activations