© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6379
    Prev
    Next
    INDEX
    Explanations

    say "poem"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Videos
    -0.18
     Articles
    -0.16
    Articles
    -0.15
     Projects
    -0.15
     Blogs
    -0.15
     documentaries
    -0.15
    Videos
    -0.15
     Books
    -0.15
     Podcasts
    -0.14
     Papers
    -0.14
    POSITIVE LOGITS
     poem
    0.13
     películ
    0.11
     questu
    0.11
     նախագ
    0.11
     ծր
    0.11
     файл
    0.10
     фильм
    0.10
    视频免费
    0.10
     თამაში
    0.10
     ֆիլմ
    0.10
    Activations Density 0.243%

    No Known Activations