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. 9145
    Prev
    Next
    INDEX
    Explanations

    创新

    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
     iverm
    -0.08
     Emilia
    -0.08
    懂
    -0.08
    inst
    -0.08
     हल
    -0.07
     couvrir
    -0.07
     दुस
    -0.07
     Tach
    -0.07
    Mel
    -0.07
     пред
    -0.07
    POSITIVE LOGITS
    તમ
    0.09
    理念
    0.09
    तम
    0.09
    -led
    0.08
    方案
    0.08
     impetus
    0.08
     ideas
    0.08
    शील
    0.08
     tecnológica
    0.08
    Chap
    0.08
    Activations Density 0.015%

    No Known Activations