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. 18914
    Prev
    Next
    INDEX
    Explanations

    completing tasks

    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
     dévo
    -0.08
     returndata
    -0.08
    аян
    -0.08
     Hôtel
    -0.08
     Durable
    -0.08
    宣布
    -0.07
     ylabel
    -0.07
    führer
    -0.07
     nearing
    -0.07
     hydrochlor
    -0.07
    POSITIVE LOGITS
     задачи
    0.12
     opdrachten
    0.12
     puzzles
    0.12
     tarefas
    0.11
     задания
    0.11
     Aufgaben
    0.11
     مشکلات
    0.11
     tasks
    0.11
     тапсыр
    0.10
     desafios
    0.10
    Activations Density 0.042%

    No Known Activations