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. 54128
    Prev
    Next
    INDEX
    Explanations

    slide

    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
     kriminal
    -0.08
     Leisure
    -0.08
     libido
    -0.08
     recreational
    -0.08
     જાણવા
    -0.07
     раствор
    -0.07
     leisure
    -0.07
    -0.07
     simmer
    -0.07
     наркот
    -0.07
    POSITIVE LOGITS
     slides
    0.10
    _slide
    0.10
     storyboard
    0.10
    Slide
    0.09
     लोगो
    0.09
    Image
    0.09
    -image
    0.09
     slide
    0.09
     ora
    0.09
     slideshow
    0.09
    Activations Density 0.006%

    No Known Activations