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. 102862
    Prev
    Next
    INDEX
    Explanations

    jokes and answers

    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
     additional
    -0.09
    Polyline
    -0.08
    pakt
    -0.07
     Cald
    -0.07
     thr
    -0.07
     eventual
    -0.07
     ['
    -0.07
     deposit
    -0.07
    six
    -0.07
    额
    -0.07
    POSITIVE LOGITS
     humor
    0.11
     Humor
    0.10
     satire
    0.10
     humorous
    0.10
     startled
    0.10
     amusing
    0.09
     sarcast
    0.09
     poign
    0.08
     conveys
    0.08
     anecdotes
    0.08
    Activations Density 0.020%

    No Known Activations