© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 30398
    Prev
    Next
    INDEX
    Explanations

    integer

    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
     bich
    -0.08
     sput
    -0.08
     soi
    -0.08
     Tus
    -0.08
    য়ার
    -0.08
    公众号
    -0.08
     Jaw
    -0.07
     Humanity
    -0.07
    Tra
    -0.07
    aurus
    -0.07
    POSITIVE LOGITS
    -valu
    0.12
     induc
    0.09
     coincid
    0.08
    mente
    0.08
    acters
    0.08
     divisible
    0.07
    値
    0.07
    ทั่วไป
    0.07
     дел
    0.07
    mv
    0.07
    Activations Density 0.050%

    No Known Activations