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. 8583
    Prev
    Next
    INDEX
    Explanations

    Agile Scrum

    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
    'arr
    -0.09
     England
    -0.08
    _EXPR
    -0.08
    owanych
    -0.08
     Boden
    -0.07
     dominant
    -0.07
     manipulated
    -0.07
    _ENGINE
    -0.07
     raça
    -0.07
     angular
    -0.07
    POSITIVE LOGITS
     অনুষ্ঠ
    0.09
    doctoral
    0.09
    (update
    0.09
     अपडेट
    0.08
     update
    0.08
    召开
    0.08
     बैठक
    0.08
     предвар
    0.08
    	update
    0.08
     atualização
    0.08
    Activations Density 0.002%

    No Known Activations