© 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. 43514
    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
     Defined
    -0.09
    ωσης
    -0.08
     Authorized
    -0.08
     आदेश
    -0.08
     Isa
    -0.08
     Approx
    -0.07
    ο
    -0.07
     pou
    -0.07
     Brett
    -0.07
     Separate
    -0.07
    POSITIVE LOGITS
     ஆகிய
    0.11
    等等
    0.10
     등이
    0.09
     എന്നിവ
    0.09
     എന്നീ
    0.08
     Wies
    0.08
     торм
    0.08
     suy
    0.07
     Tmax
    0.07
    。。。
    0.07
    Activations Density 0.252%

    No Known Activations