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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 97197
    Prev
    Next
    INDEX
    Explanations

    Trading

    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
     영화
    -0.11
    django
    -0.10
    ​—
    -0.10
     vélo
    -0.10
     flask
    -0.10
     திரைப்பட
    -0.10
    .recyclerview
    -0.10
    urlpatterns
    -0.09
     사진
    -0.09
    (noun
    -0.09
    POSITIVE LOGITS
     Trading
    0.18
     Forex
    0.18
    Trading
    0.17
     trader
    0.17
    Forex
    0.16
     BUY
    0.16
     التداول
    0.16
     forex
    0.16
     Trader
    0.16
    Trader
    0.16
    Activations Density 0.021%

    No Known Activations