© 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. 70065
    Prev
    Next
    INDEX
    Explanations

    math

    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
     notar
    -0.08
     süreç
    -0.08
     overt
    -0.08
     diária
    -0.07
     प्रक्र
    -0.07
     પ્રક્ર
    -0.07
     daily
    -0.07
     liter
    -0.07
     seemed
    -0.07
     dripping
    -0.07
    POSITIVE LOGITS
    одӣ
    0.09
    څ
    0.08
    盗
    0.08
    никам
    0.08
     merchandise
    0.08
     Frequ
    0.08
    .CONTENT
    0.08
    тік
    0.08
    requencies
    0.08
     запрещ
    0.08
    Activations Density 0.006%

    No Known Activations