Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 18965
    Prev
    Next
    INDEX
    Explanations

    science

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reiz
    -0.09
     repeal
    -0.09
    报价
    -0.08
    'annonce
    -0.08
    (period
    -0.08
    售价
    -0.08
    bets
    -0.08
     PURCHASE
    -0.08
    上映
    -0.08
     فات
    -0.07
    POSITIVE LOGITS
     theory
    0.18
     science
    0.15
     Theory
    0.15
     mathematics
    0.15
     medicine
    0.15
     науки
    0.14
     sciences
    0.14
    Theory
    0.14
     astronomy
    0.14
     Theorie
    0.13
    Activations Density 0.086%

    No Known Activations