© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51963
    Prev
    Next
    INDEX
    Explanations

    Product/technical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _UI
    -0.09
    -ui
    -0.08
    (UI
    -0.08
    Cisco
    -0.08
    ccak
    -0.07
    /ui
    -0.07
     Impl
    -0.07
    /color
    -0.07
    DAOImpl
    -0.07
     gc
    -0.07
    POSITIVE LOGITS
    か
    0.09
     plaatsen
    0.08
    heden
    0.08
    lık
    0.08
    larda
    0.08
    ısından
    0.08
    plaatsen
    0.08
     praks
    0.08
    liği
    0.08
     nes
    0.08
    Activations Density 0.000%

    No Known Activations