© 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. 48208
    Prev
    Next
    INDEX
    Explanations

    os

    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
     खेत
    -0.08
    ึ้น
    -0.08
    ายน
    -0.08
     бүл
    -0.08
     बाहर
    -0.08
     dépend
    -0.07
     распис
    -0.07
     UID
    -0.07
    _targets
    -0.07
    лым
    -0.07
    POSITIVE LOGITS
     débarr
    0.07
    hibit
    0.07
    406
    0.07
    messe
    0.07
    \Controller
    0.07
    teacher
    0.07
     competencies
    0.07
    0.07
     azi
    0.07
     concussion
    0.07
    Activations Density 0.000%

    No Known Activations