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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110702
    Prev
    Next
    INDEX
    Explanations

    Naruto and Freedom Planet fanfiction

    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
    贷款
    -0.11
    业务
    -0.09
    融资
    -0.09
    智慧
    -0.09
    _payment
    -0.09
    打印
    -0.08
     Financing
    -0.08
    卓
    -0.08
     insurer
    -0.08
     혁
    -0.08
    POSITIVE LOGITS
     cosplay
    0.15
     fandom
    0.14
     Anime
    0.13
    Anime
    0.12
     anime
    0.12
     hentai
    0.12
     ரசிக
    0.12
    動漫
    0.11
    动漫
    0.11
     fãs
    0.11
    Activations Density 0.407%

    No Known Activations