Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 58664
    Prev
    Next
    INDEX
    Explanations

    equilateral triangles

    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
     disappointing
    -0.08
     Arena
    -0.08
    .topic
    -0.08
    880
    -0.08
     Concept
    -0.08
    .author
    -0.08
    Concept
    -0.08
    concept
    -0.08
     Quand
    -0.08
     conceitos
    -0.08
    POSITIVE LOGITS
     निर्माण
    0.09
    。)
    0.08
     impose
    0.08
     инс
    0.08
     बनाने
    0.08
     الحرة
    0.08
     burgl
    0.08
     બનાવવા
    0.08
     burglary
    0.08
     dolayı
    0.08
    Activations Density 0.012%

    No Known Activations