© 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. 11-RESID-POST-AA
    11. 71494
    Prev
    Next
    INDEX
    Explanations

    prompt

    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
    -lived
    -0.07
     எதிர
    -0.07
     rumored
    -0.07
     Henderson
    -0.07
     regula
    -0.07
    默
    -0.07
    _called
    -0.07
     Malone
    -0.07
    秘
    -0.07
     supported
    -0.07
    POSITIVE LOGITS
     пожалуйста
    0.08
    氏
    0.08
     waarop
    0.08
     contrario
    0.08
     Pizza
    0.08
     vị
    0.08
    ?,?,?,?,
    0.08
     kənd
    0.08
     lekker
    0.08
     phố
    0.08
    Activations Density 0.008%

    No Known Activations