© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 20512
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    控制
    -0.09
     manager
    -0.08
     التحكم
    -0.08
     CLI
    -0.08
    controller
    -0.08
    manager
    -0.08
     gerenciamento
    -0.08
     nhóm
    -0.08
    服务器
    -0.08
     کنترل
    -0.08
    POSITIVE LOGITS
     heritage
    0.16
    文化
    0.15
    精神
    0.14
     patrimoine
    0.14
     문화
    0.13
     мәдә
    0.13
     संस्कृति
    0.13
     esencia
    0.13
    魅
    0.13
     espíritu
    0.13
    Activations Density 0.019%

    No Known Activations