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. 112865
    Prev
    Next
    INDEX
    Explanations

    legal proceedings

    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
     hubs
    -0.08
    可靠吗
    -0.08
    Singleton
    -0.08
     adapters
    -0.08
    Categorias
    -0.08
     substr
    -0.07
    raquo
    -0.07
    gz
    -0.07
     substring
    -0.07
     filtering
    -0.07
    POSITIVE LOGITS
     sentencing
    0.14
     sentenced
    0.13
     കോടതി
    0.12
     अदालत
    0.11
     আদাল
    0.11
     juez
    0.11
    法院
    0.11
     juiz
    0.10
     condam
    0.10
     doktor
    0.10
    Activations Density 0.062%

    No Known Activations