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. 49140
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    ongan
    -0.08
     refrigeration
    -0.08
    nem
    -0.08
     stod
    -0.08
     bulky
    -0.08
     Anch
    -0.08
    orschung
    -0.07
     refrigerated
    -0.07
    융
    -0.07
    =value
    -0.07
    POSITIVE LOGITS
    .count
    0.19
     count
    0.19
     counts
    0.18
    	count
    0.18
     COUNT
    0.18
     counting
    0.17
     تعداد
    0.17
     Count
    0.17
    (count
    0.17
     Counting
    0.17
    Activations Density 0.072%

    No Known Activations