© 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. 11-RESID-POST-AA
    11. 75547
    Prev
    Next
    INDEX
    Explanations

    Kronecker delta notation

    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
     Beweg
    -0.08
    .zip
    -0.08
    .br
    -0.08
    -gap
    -0.08
     movimientos
    -0.08
     movements
    -0.07
     কাট
    -0.07
     Gap
    -0.07
     wines
    -0.07
    Gap
    -0.07
    POSITIVE LOGITS
     아니라
    0.10
     وعلى
    0.09
    しく
    0.09
     بإ
    0.08
     Perse
    0.08
    çar
    0.08
     아�
    0.07
     కాదు
    0.07
    igus
    0.07
     strcmp
    0.07
    Activations Density 0.010%

    No Known Activations