© 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. 51924
    Prev
    Next
    INDEX
    Explanations

    Why

    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
    ucker
    -0.07
    ][]
    -0.07
     )[
    -0.07
    anaan
    -0.07
    @class
    -0.07
    *)((
    -0.07
    ubs
    -0.06
     ][
    -0.06
    mele
    -0.06
     {↵
    -0.06
    POSITIVE LOGITS
     why
    0.76
    Why
    0.71
     Why
    0.69
    why
    0.68
     waarom
    0.67
     warum
    0.67
    为什么
    0.65
     pourquoi
    0.65
    Warum
    0.64
    Pourquoi
    0.64
    Activations Density 0.464%

    No Known Activations