© 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. 63841
    Prev
    Next
    INDEX
    Explanations

    coding 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
    etchup
    -0.09
     이어
    -0.09
    ieties
    -0.08
    stype
    -0.08
    れる
    -0.08
    とは
    -0.08
     unmarried
    -0.08
     mince
    -0.08
    大量
    -0.08
    унда
    -0.08
    POSITIVE LOGITS
     pul
    0.09
    pul
    0.08
     Ges
    0.08
     Cuban
    0.08
     Church
    0.07
     Cheney
    0.07
     Seguridad
    0.07
     Pul
    0.07
     rising
    0.07
     gro
    0.07
    Activations Density 0.004%

    No Known Activations