© 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. 70428
    Prev
    Next
    INDEX
    Explanations

    Animation frames and performance

    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
     graduated
    -0.08
     "','
    -0.08
     grammar
    -0.07
     clin
    -0.07
     "{\"
    -0.07
     Json
    -0.07
    \Models
    -0.07
     gramm
    -0.07
    .rules
    -0.07
    Json
    -0.07
    POSITIVE LOGITS
     नभ
    0.09
     performant
    0.09
    Apple
    0.08
     عصر
    0.08
     Apple
    0.08
     Başkan
    0.08
     Худ
    0.08
    랫폼
    0.08
    atever
    0.08
     aangepast
    0.08
    Activations Density 0.001%

    No Known Activations