© 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. 110723
    Prev
    Next
    INDEX
    Explanations

    File

    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
    דת
    -0.08
    enda
    -0.08
    דות
    -0.08
     המ
    -0.07
     SMEs
    -0.07
     Chan
    -0.07
    。当然
    -0.07
    /tree
    -0.07
    -G
    -0.07
    .correct
    -0.07
    POSITIVE LOGITS
    'ak
    0.09
    rp
    0.08
    ../../../
    0.08
    iž
    0.08
     rq
    0.08
    éni
    0.07
    arul
    0.07
     작업
    0.07
    paper
    0.07
    _rsp
    0.07
    Activations Density 0.002%

    No Known Activations