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. 78492
    Prev
    Next
    INDEX
    Explanations

    programming polymorphism/overloading

    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
     propel
    -0.09
     empower
    -0.09
    upuk
    -0.09
    .ticket
    -0.08
    itaj
    -0.08
     empowerment
    -0.08
    主管
    -0.08
     empowers
    -0.08
    ণা
    -0.08
    anggung
    -0.08
    POSITIVE LOGITS
     Differ
    0.09
     specificity
    0.08
     differing
    0.08
     Incorrect
    0.08
     sorting
    0.08
     incorrect
    0.08
     resolved
    0.08
     charges
    0.08
     unterschiedliche
    0.08
     Щ
    0.08
    Activations Density 0.003%

    No Known Activations