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. 44011
    Prev
    Next
    INDEX
    Explanations

    confidence intervals

    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
    competitive
    -0.08
     Competition
    -0.08
    깨
    -0.08
    ด
    -0.08
    ipes
    -0.08
     icon
    -0.08
     apoptosis
    -0.08
     apopt
    -0.08
     गाँव
    -0.08
    음
    -0.08
    POSITIVE LOGITS
     confidence
    0.16
     Confidence
    0.15
    Confidence
    0.15
    confidence
    0.14
    -confidence
    0.13
     percentile
    0.12
     confident
    0.11
    .bounds
    0.10
     uncertainty
    0.10
     anxiety
    0.10
    Activations Density 0.006%

    No Known Activations