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. 11-RESID-POST-AA
    6. 24415
    Prev
    Next
    INDEX
    Explanations

    receive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ::-
    -0.08
     Ras
    -0.08
     dahil
    -0.08
    Gob
    -0.08
    -have
    -0.08
    abolism
    -0.07
     Mighty
    -0.07
    bene
    -0.07
     lumen
    -0.07
     夏
    -0.07
    POSITIVE LOGITS
     insights
    0.13
     जानकारी
    0.12
     정보를
    0.12
    ข้อมูล
    0.11
     معلومات
    0.11
     подроб
    0.11
    'informations
    0.11
     информацию
    0.11
     informações
    0.11
     πληροφο
    0.10
    Activations Density 0.097%

    No Known Activations