© 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. 23-RESID-POST-AA
    11. 48563
    Prev
    Next
    INDEX
    Explanations

    в

    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
     ajili
    -0.09
    čenja
    -0.08
    (if
    -0.08
    richtung
    -0.07
    stående
    -0.07
     activities
    -0.07
    idot
    -0.07
    (for
    -0.07
    ательства
    -0.07
    (target
    -0.07
    POSITIVE LOGITS
    прочем
    0.18
     итоге
    0.18
     свою
    0.15
     частности
    0.14
    另一方面
    0.14
     то
    0.14
     consequência
    0.13
     última
    0.13
     сваю
    0.13
     результате
    0.13
    Activations Density 0.021%

    No Known Activations