© 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. 30313
    Prev
    Next
    INDEX
    Explanations

    intelligence

    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
    eliz
    -0.09
     aceptar
    -0.08
     teleport
    -0.08
    lera
    -0.08
    ortu
    -0.08
     reclamar
    -0.08
     fitting
    -0.08
     répar
    -0.08
     akzept
    -0.08
    drag
    -0.08
    POSITIVE LOGITS
     развед
    0.13
     SWOT
    0.12
     Gartner
    0.12
     scouting
    0.12
     intelligence
    0.12
     renseign
    0.11
     Intelligence
    0.11
    情報
    0.11
     분석
    0.11
     analyst
    0.11
    Activations Density 0.047%

    No Known Activations