© 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. 111332
    Prev
    Next
    INDEX
    Explanations

    parentheses

    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
    ání
    -0.08
    pin
    -0.08
     স
    -0.07
     dokon
    -0.07
    _p
    -0.07
     sac
    -0.07
    -0.07
    _re
    -0.07
     প
    -0.07
    _es
    -0.07
    POSITIVE LOGITS
     trochu
    0.09
     TString
    0.09
     Hotels
    0.08
     Economía
    0.08
     Türkiye
    0.08
     figuring
    0.08
     Türki
    0.08
     Economia
    0.08
    .Files
    0.08
     крим
    0.08
    Activations Density 0.000%
    No Known Activations