© 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. 23-RESID-POST-AA
    11. 49933
    Prev
    Next
    INDEX
    Explanations

    say "R" or "Workbook"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     случ
    -0.08
     chargers
    -0.08
    _CHARACTER
    -0.08
    ngo
    -0.07
     Ai
    -0.07
    法国
    -0.07
    (char
    -0.07
     wchar
    -0.07
    _CHAR
    -0.07
    jg
    -0.07
    POSITIVE LOGITS
    Workbook
    0.10
    Paging
    0.09
    Callback
    0.08
    Screenshot
    0.08
    urnal
    0.08
    tar
    0.08
    Snapshot
    0.08
    Tar
    0.08
     பதிவு
    0.08
    Target
    0.08
    Activations Density 0.001%

    No Known Activations