© 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. 44348
    Prev
    Next
    INDEX
    Explanations

    excel file extensions

    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
     lift
    -0.08
     illustrated
    -0.08
    책
    -0.07
     illustrate
    -0.07
    ย
    -0.07
    Bench
    -0.07
    Invert
    -0.07
     پیش
    -0.07
    /community
    -0.07
    laws
    -0.07
    POSITIVE LOGITS
    年代
    0.10
    sv
    0.10
    SSFWorkbook
    0.09
    /vnd
    0.08
     antiqu
    0.08
     అమెరిక
    0.08
     અમેરિક
    0.08
    xls
    0.08
     SV
    0.08
     Españ
    0.08
    Activations Density 0.004%

    No Known Activations