© 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. 69315
    Prev
    Next
    INDEX
    Explanations

    integers and the variable i

    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
    Debit
    -0.09
    Candidate
    -0.07
    ierre
    -0.07
     anat
    -0.07
    Apa
    -0.07
     مدار
    -0.07
    !/
    -0.07
     링크
    -0.07
    Uid
    -0.07
    Speed
    -0.07
    POSITIVE LOGITS
     seamlessly
    0.08
     ناخ
    0.08
    _rooms
    0.08
     Beaches
    0.08
     помещений
    0.08
     synerg
    0.07
     cof
    0.07
    _sites
    0.07
     hodnot
    0.07
    .install
    0.07
    Activations Density 0.017%

    No Known Activations