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. 111661
    Prev
    Next
    INDEX
    Explanations

    history

    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
    Graphs
    -0.09
     ideology
    -0.09
     substantive
    -0.08
     incumb
    -0.08
     ideological
    -0.08
    Issues
    -0.08
     discurs
    -0.07
     graphs
    -0.07
    graphs
    -0.07
    同志
    -0.07
    POSITIVE LOGITS
     medicinal
    0.10
     botan
    0.10
     хим
    0.09
     рецеп
    0.09
     Jardin
    0.09
     Vitamin
    0.09
     centuries
    0.09
     Cottage
    0.09
     농
    0.08
     המל
    0.08
    Activations Density 0.043%

    No Known Activations