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. 65062
    Prev
    Next
    INDEX
    Explanations

    comedic text

    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
     STEM
    -0.09
    .download
    -0.08
    .dataset
    -0.08
     {:.
    -0.08
    长期
    -0.08
    .variable
    -0.08
     firestore
    -0.08
    .Dataset
    -0.08
     '.'
    -0.08
     nourishment
    -0.08
    POSITIVE LOGITS
     comedic
    0.24
     humorous
    0.23
     hilarious
    0.21
     हास
    0.21
     Comedy
    0.21
     comedy
    0.21
     antics
    0.21
     humor
    0.20
    Comedy
    0.20
     playful
    0.20
    Activations Density 0.116%

    No Known Activations