© 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 EvalsExportsAPI 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. 113240
    Prev
    Next
    INDEX
    Explanations

    humans

    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
    uner
    -0.07
     жит
    -0.07
     pion
    -0.07
     amare
    -0.07
    artan
    -0.07
     mục
    -0.07
     življen
    -0.07
    ೃತ
    -0.07
     ترین
    -0.07
     уку
    -0.07
    POSITIVE LOGITS
     Borussia
    0.10
    opolitan
    0.09
    /eclipse
    0.09
    _DEPTH
    0.09
    .Depth
    0.08
    bug
    0.08
     Depth
    0.08
    Teen
    0.08
     pleinement
    0.08
     manufactures
    0.08
    Activations Density 0.002%

    No Known Activations