© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102974
    Prev
    Next
    INDEX
    Explanations

    with

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /main
    -0.09
    /core
    -0.09
    aniwang
    -0.09
     প্রধান
    -0.09
    /Main
    -0.08
    /gin
    -0.08
    _Context
    -0.08
     mainstream
    -0.08
    edevším
    -0.08
     болуы
    -0.07
    POSITIVE LOGITS
     additional
    0.13
     subdivisions
    0.13
     adicional
    0.13
     subdivision
    0.13
     supplémentaire
    0.13
     dodatk
    0.12
     subdiv
    0.12
     thêm
    0.12
    additional
    0.12
     tambahan
    0.12
    Activations Density 0.054%

    No Known Activations