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. 11750
    Prev
    Next
    INDEX
    Explanations

    bullets

    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
     expose
    -0.08
     публич
    -0.08
     expos
    -0.08
    itorial
    -0.08
    welcome
    -0.07
     architectural
    -0.07
     swiper
    -0.07
     Lie
    -0.07
    _UI
    -0.07
     localisation
    -0.07
    POSITIVE LOGITS
     गोली
    0.09
     benchmarks
    0.09
     densities
    0.09
     pellets
    0.08
     fertilizers
    0.08
    Benchmark
    0.08
     Bench
    0.08
     Powder
    0.08
     farmland
    0.08
     الثقيلة
    0.08
    Activations Density 0.013%

    No Known Activations