© 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 EvalsExportsinterp-engineNEWAPI 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. 70076
    Prev
    Next
    INDEX
    Explanations

    work

    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
    ubert
    -0.07
    geb
    -0.07
    /client
    -0.07
    weiter
    -0.07
    .k
    -0.07
    requirements
    -0.07
    .Builder
    -0.07
     라
    -0.07
    ur
    -0.07
    src
    -0.07
    POSITIVE LOGITS
    哪些
    0.10
     nhất
    0.10
     davvero
    0.09
    ดีที่สุด
    0.09
     eficaz
    0.09
     efektif
    0.09
     cuáles
    0.08
     ביותר
    0.08
     najbardziej
    0.08
     कौन
    0.08
    Activations Density 0.030%

    No Known Activations