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. 88060
    Prev
    Next
    INDEX
    Explanations

    medicine and healthcare

    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
     bondage
    -0.11
     pleasures
    -0.10
     barter
    -0.10
     정치
    -0.09
    زين
    -0.09
     carefree
    -0.09
    Tween
    -0.09
     zvinhu
    -0.09
     windy
    -0.09
    政治
    -0.09
    POSITIVE LOGITS
     clinical
    0.19
    Clinical
    0.18
     clinically
    0.18
     Clinical
    0.18
    clinical
    0.17
    .patient
    0.17
     patient
    0.17
     clinicians
    0.17
     દર્દ
    0.16
     मरीज
    0.16
    Activations Density 0.027%

    No Known Activations