© 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. 47960
    Prev
    Next
    INDEX
    Explanations

    استخ

    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
    card
    -0.08
     hará
    -0.08
    vict
    -0.07
    cards
    -0.07
    ge
    -0.07
    jų
    -0.07
    jom
    -0.07
    cura
    -0.07
    гаа
    -0.07
     کند
    -0.07
    POSITIVE LOGITS
    دم
    0.17
    دمت
    0.15
    لاص
    0.14
    دمة
    0.12
    دمات
    0.12
    د
    0.10
    ד
    0.09
     스마트
    0.09
     टीवी
    0.09
    ensively
    0.08
    Activations Density 0.000%

    No Known Activations