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. 90999
    Prev
    Next
    INDEX
    Explanations

    energetic

    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
     langzaam
    -0.09
     eleg
    -0.08
     Slowly
    -0.08
     silently
    -0.08
    (gray
    -0.08
     sombra
    -0.08
    Silent
    -0.08
     langsam
    -0.08
     slowly
    -0.08
     slow
    -0.08
    POSITIVE LOGITS
     lively
    0.19
     enthusiasm
    0.17
     vibrant
    0.16
     enthousiasme
    0.16
     enthusiastic
    0.16
     excitement
    0.16
     upbeat
    0.15
     весел
    0.15
     exuber
    0.14
     alegre
    0.14
    Activations Density 0.260%

    No Known Activations