Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130931
    Prev
    Next
    INDEX
    Explanations

    RimWorld definitions

    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
     Nguyễn
    -0.12
     Bakı
    -0.10
     Kou
    -0.10
     Guangzhou
    -0.10
     Suzuki
    -0.10
    淘宝
    -0.09
     Alibaba
    -0.09
    广东
    -0.09
    广州
    -0.09
     Osaka
    -0.09
    POSITIVE LOGITS
     pawn
    0.14
    Pawn
    0.14
     Pawn
    0.14
     Thing
    0.13
    Thing
    0.12
     Rim
    0.12
     Def
    0.12
     Mathf
    0.11
     defs
    0.11
    Def
    0.11
    Activations Density 0.002%

    No Known Activations