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. 53008
    Prev
    Next
    INDEX
    Explanations

    arteries and blood vessels

    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
    _keyboard
    -0.09
     游戏
    -0.08
     muse
    -0.08
     conversational
    -0.08
     Reiki
    -0.08
     సంగీత
    -0.08
     ritual
    -0.08
    =m
    -0.08
     improvis
    -0.08
    girl
    -0.08
    POSITIVE LOGITS
     aneur
    0.14
     arteries
    0.12
     artery
    0.11
     धम
    0.10
     coronary
    0.10
     plaque
    0.10
     cholesterol
    0.10
    theros
    0.10
     arterial
    0.10
     plaques
    0.10
    Activations Density 0.005%

    No Known Activations