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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 65476
    Prev
    Next
    INDEX
    Explanations

    use

    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
     đăng
    -0.08
    _HASH
    -0.07
     qora
    -0.07
    _train
    -0.07
     싶은
    -0.07
    咪
    -0.07
     Aberdeen
    -0.07
     получите
    -0.07
     κάν
    -0.07
    nim
    -0.07
    POSITIVE LOGITS
    маган
    0.07
    단
    0.07
     illustrating
    0.07
    ировку
    0.07
     Ish
    0.07
    )).↵
    0.07
    ிருந்து
    0.07
    져
    0.07
     ambient
    0.07
    ındaki
    0.07
    Activations Density 0.065%

    No Known Activations