© 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. 70307
    Prev
    Next
    INDEX
    Explanations

    Santa Fe, New Mexico

    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
     stretch
    -0.07
    itaan
    -0.07
     ülk
    -0.07
    endera
    -0.07
     sosyal
    -0.07
    _secondary
    -0.07
    estr
    -0.07
    _peak
    -0.07
     Peaks
    -0.07
     Hansen
    -0.07
    POSITIVE LOGITS
    Ali
    0.09
    gharị
    0.09
     aliqu
    0.09
    /ws
    0.08
    ghar
    0.08
    롭게
    0.08
     ingew
    0.08
     Ali
    0.08
     SP
    0.08
    ution
    0.08
    Activations Density 0.017%

    No Known Activations