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. 119760
    Prev
    Next
    INDEX
    Explanations

    Containers

    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
    stdin
    -0.07
     zentrale
    -0.07
     barbar
    -0.07
     empleo
    -0.07
     vitamina
    -0.07
    uncate
    -0.07
     stretched
    -0.07
     excelente
    -0.07
     tremendous
    -0.07
     heb
    -0.07
    POSITIVE LOGITS
     negligible
    0.10
     изделия
    0.10
     المعدات
    0.10
     overhead
    0.09
     мебели
    0.09
     meubels
    0.09
     jackets
    0.09
     Gerald
    0.09
     incurred
    0.08
     изделий
    0.08
    Activations Density 0.009%

    No Known Activations