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. 42015
    Prev
    Next
    INDEX
    Explanations

    diagram

    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
     spécialisée
    -0.08
    خصصة
    -0.08
     Tango
    -0.08
     Stool
    -0.07
     wandering
    -0.07
     GAN
    -0.07
     specialize
    -0.07
     kommunik
    -0.07
     hunger
    -0.07
     spécialis
    -0.07
    POSITIVE LOGITS
     depicts
    0.09
    (graph
    0.08
     graphs
    0.08
     diagram
    0.08
     graph
    0.08
     nice
    0.08
    Vertices
    0.08
     diagrams
    0.08
     Diagram
    0.08
     caption
    0.08
    Activations Density 0.012%

    No Known Activations