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. 49125
    Prev
    Next
    INDEX
    Explanations

    》的

    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
     bun
    -0.08
     célé
    -0.08
    龄
    -0.08
     approxim
    -0.07
     broadband
    -0.07
     geh
    -0.07
     puntu
    -0.07
    ଗ
    -0.07
     unh
    -0.07
     gata
    -0.07
    POSITIVE LOGITS
    ENUM
    0.08
     oner
    0.08
    .twig
    0.08
     jedhu
    0.08
    _indent
    0.08
     Он
    0.08
    @$
    0.08
     삼
    0.07
    ойд
    0.07
    _NV
    0.07
    Activations Density 0.016%

    No Known Activations