© 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 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. 113777
    Prev
    Next
    INDEX
    Explanations

    to

    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
    ాధ
    -0.08
     столк
    -0.08
     successive
    -0.08
    鸿
    -0.08
     powers
    -0.08
     Bany
    -0.08
     معا
    -0.07
     firsthand
    -0.07
    &oacute
    -0.07
     traced
    -0.07
    POSITIVE LOGITS
    格式
    0.10
     Strict
    0.10
     obey
    0.09
    Formatting
    0.09
     Allowed
    0.09
     FORMAT
    0.09
    Strict
    0.09
    规范
    0.09
     Formatting
    0.09
    strict
    0.09
    Activations Density 0.017%

    No Known Activations