© 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. 23-RESID-POST-AA
    11. 50139
    Prev
    Next
    INDEX
    Explanations

    塞

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    programma
    -0.09
    רכז
    -0.09
    rüstung
    -0.08
     Día
    -0.08
     intend
    -0.08
    cher
    -0.08
     fortified
    -0.08
    hasa
    -0.08
    .runners
    -0.08
     programma
    -0.08
    POSITIVE LOGITS
     avoidance
    0.14
    Avoid
    0.14
    避免
    0.13
     Avoid
    0.13
    avoid
    0.12
     avoid
    0.12
     evitare
    0.12
     evitar
    0.12
     evit
    0.11
     tránh
    0.11
    Activations Density 0.003%

    No Known Activations