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. 76028
    Prev
    Next
    INDEX
    Explanations

    advice and instructions

    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
     exhib
    -0.08
     verursacht
    -0.08
     xảy
    -0.08
     ligand
    -0.07
     lief
    -0.07
    _test
    -0.07
     erotic
    -0.07
     bson
    -0.07
     ঘট
    -0.07
     ugly
    -0.07
    POSITIVE LOGITS
     советы
    0.17
     advice
    0.16
     advises
    0.16
     advising
    0.15
     advised
    0.15
     Tipps
    0.15
     recommendations
    0.14
     consejos
    0.14
    建议
    0.14
     recommended
    0.14
    Activations Density 0.331%

    No Known Activations