© 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. 23-RESID-POST-AA
    11. 50439
    Prev
    Next
    INDEX
    Explanations

    pre

    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
    IEWS
    -0.09
    elijks
    -0.09
     উপ
    -0.09
    Pending
    -0.08
    .pending
    -0.08
    析
    -0.08
    ría
    -0.08
    .Pending
    -0.08
    ызы
    -0.08
     Pending
    -0.08
    POSITIVE LOGITS
    amble
    0.15
    disposing
    0.14
    lude
    0.14
    fetch
    0.14
    munition
    0.14
    -existing
    0.14
    clude
    0.14
    cludes
    0.13
    conditions
    0.13
    cluding
    0.13
    Activations Density 0.021%

    No Known Activations