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. 60649
    Prev
    Next
    INDEX
    Explanations

    conventions

    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
     malfunction
    -0.08
    equal
    -0.08
    _counts
    -0.08
     nødvendig
    -0.08
    _equal
    -0.08
     позже
    -0.07
     народа
    -0.07
     airt
    -0.07
    olithic
    -0.07
     calculates
    -0.07
    POSITIVE LOGITS
    规范
    0.16
     conventions
    0.16
    遵
    0.14
     adherence
    0.13
     practices
    0.12
     hábitos
    0.11
     hygiene
    0.11
     naming
    0.11
     práticas
    0.11
     guidelines
    0.11
    Activations Density 0.017%

    No Known Activations