© 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. 64858
    Prev
    Next
    INDEX
    Explanations

    Chinese astrology

    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
     numbering
    -0.08
     JCheck
    -0.08
     Vim
    -0.08
    _buttons
    -0.08
    Checkbox
    -0.08
    _default
    -0.07
    .flag
    -0.07
     flagged
    -0.07
    -positive
    -0.07
    (control
    -0.07
    POSITIVE LOGITS
    YYYY
    0.09
     empowering
    0.09
     راز
    0.08
    秘诀
    0.08
     SSA
    0.07
    yramid
    0.07
    ktime
    0.07
     veil
    0.07
    生日
    0.07
     өнер
    0.07
    Activations Density 0.001%

    No Known Activations