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. 112140
    Prev
    Next
    INDEX
    Explanations

    anime

    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
     OSHA
    -0.12
     Medicare
    -0.10
     Walgreens
    -0.10
     phosphorus
    -0.09
     Oregon
    -0.09
     Cheney
    -0.09
     absentee
    -0.09
     subpoena
    -0.09
    Measurement
    -0.09
     bees
    -0.09
    POSITIVE LOGITS
     anime
    0.20
     manga
    0.19
    动漫
    0.18
     Anime
    0.17
    動漫
    0.16
     hentai
    0.16
    Anime
    0.15
    漫画
    0.15
     Manga
    0.15
     Naruto
    0.14
    Activations Density 0.075%

    No Known Activations