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. 112134
    Prev
    Next
    INDEX
    Explanations

    Output generation

    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
     accidentally
    -0.11
     слуш
    -0.09
    仔
    -0.08
     inadvertently
    -0.08
    .Parser
    -0.08
     luisteren
    -0.08
    监听
    -0.08
     écouter
    -0.08
     прояв
    -0.08
     Cheer
    -0.08
    POSITIVE LOGITS
     actionable
    0.14
     confidence
    0.10
     rankings
    0.10
     recommendations
    0.09
     ranking
    0.09
     ranked
    0.09
     indicando
    0.09
     insights
    0.09
     تقرير
    0.08
     identifies
    0.08
    Activations Density 0.060%

    No Known Activations