© 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. 70039
    Prev
    Next
    INDEX
    Explanations

    single

    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
     beschäd
    -0.08
    Streamer
    -0.08
     handwriting
    -0.07
    yrinth
    -0.07
     streamer
    -0.07
     exceeding
    -0.07
    forth
    -0.07
    thin
    -0.07
    ALLY
    -0.07
     qa
    -0.07
    POSITIVE LOGITS
     célib
    0.10
    男女
    0.09
    婚
    0.09
     married
    0.09
     bırak
    0.09
    状態
    0.09
    /ar
    0.08
     divorce
    0.08
    stående
    0.08
    青年
    0.08
    Activations Density 0.011%

    No Known Activations