© 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. 71246
    Prev
    Next
    INDEX
    Explanations

    Numerical/math methods

    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
    مند
    -0.09
    ерг
    -0.08
    تش
    -0.08
     purse
    -0.07
    তি
    -0.07
    Dimensions
    -0.07
     tumors
    -0.07
     Dimensions
    -0.07
    emoji
    -0.07
    ্ত
    -0.07
    POSITIVE LOGITS
     தொடர
    0.08
     расс
    0.08
    .solve
    0.08
    verfahren
    0.08
    Fal
    0.08
    .goto
    0.08
    ucao
    0.07
     sludge
    0.07
     domic
    0.07
     aplicado
    0.07
    Activations Density 0.006%

    No Known Activations