© 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. 70230
    Prev
    Next
    INDEX
    Explanations

    share/sharing

    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
     backdrop
    -0.08
     spinach
    -0.08
    gestellt
    -0.07
     Floyd
    -0.07
    本人
    -0.07
    lying
    -0.07
    nad
    -0.07
     Peg
    -0.07
    চ্চ
    -0.07
    Peg
    -0.07
    POSITIVE LOGITS
     פעולה
    0.15
     sẻ
    0.14
    分享
    0.13
     share
    0.11
     શેર
    0.11
     分享
    0.10
     പങ്ക
    0.10
    共享
    0.10
    .share
    0.10
     साझा
    0.10
    Activations Density 0.065%

    No Known Activations