© 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. 71204
    Prev
    Next
    INDEX
    Explanations

    cent

    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
    하지만
    -0.08
     notebook
    -0.08
     huit
    -0.08
     కాల
    -0.07
    명이
    -0.07
    _KEEP
    -0.07
    .keep
    -0.07
     timp
    -0.07
     succ
    -0.07
    명을
    -0.07
    POSITIVE LOGITS
    طات
    0.08
     metus
    0.08
     أط
    0.08
     يت
    0.08
    velopment
    0.08
    zada
    0.08
     بدأ
    0.08
    mlar
    0.07
     Geo
    0.07
    yses
    0.07
    Activations Density 0.001%

    No Known Activations