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. 59474
    Prev
    Next
    INDEX
    Explanations

    linear

    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
     transparency
    -0.09
    透明
    -0.09
     transparent
    -0.09
     Transparency
    -0.08
     näk
    -0.08
    даў
    -0.08
     прозрач
    -0.08
     Drawing
    -0.08
     lada
    -0.08
    drawing
    -0.08
    POSITIVE LOGITS
    ೕ
    0.08
    শ
    0.07
    �
    0.07
     শন
    0.07
    uniq
    0.07
    Throws
    0.07
    शल
    0.07
     türlü
    0.07
     divergence
    0.07
    ndef
    0.07
    Activations Density 0.003%

    No Known Activations