© 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. 71161
    Prev
    Next
    INDEX
    Explanations

    from

    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
     vowel
    -0.08
     sigue
    -0.08
    iru
    -0.08
    cimientos
    -0.07
    ntl
    -0.07
    .spin
    -0.07
    <Table
    -0.07
     máli
    -0.07
    Consume
    -0.07
     okwu
    -0.07
    POSITIVE LOGITS
    201
    0.09
     perioden
    0.09
     dhin
    0.08
    近日
    0.07
     Gan
    0.07
    putable
    0.07
     laboratories
    0.07
     Watts
    0.07
     generations
    0.07
     veckan
    0.07
    Activations Density 0.053%

    No Known Activations