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. 26732
    Prev
    Next
    INDEX
    Explanations

    recovery

    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
     फैस
    -0.08
     विज
    -0.08
    प्रिय
    -0.08
     cruel
    -0.08
     अस्पताल
    -0.07
    ुभ
    -0.07
    <Create
    -0.07
     ruthless
    -0.07
    .Tasks
    -0.07
    ्ब
    -0.07
    POSITIVE LOGITS
    走势
    0.13
     trends
    0.13
    趋势
    0.11
    trend
    0.11
     Trends
    0.11
     trend
    0.10
    Trend
    0.10
     тенден
    0.10
     downturn
    0.09
     байқ
    0.09
    Activations Density 0.069%

    No Known Activations