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. 112236
    Prev
    Next
    INDEX
    Explanations

    review

    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
     рисун
    -0.09
    >>();↵
    -0.08
    จำนวน
    -0.08
     години
    -0.08
    iormente
    -0.08
     conspiracy
    -0.08
    .Employee
    -0.07
     tuig
    -0.07
     creatividad
    -0.07
     cirka
    -0.07
    POSITIVE LOGITS
     embargo
    0.09
    -derived
    0.08
     thoroughly
    0.08
    全面
    0.08
    _TOTAL
    0.08
     الكامل
    0.08
    worthiness
    0.08
     полном
    0.08
     അഭ
    0.08
    sandbox
    0.07
    Activations Density 0.049%

    No Known Activations