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. 75983
    Prev
    Next
    INDEX
    Explanations

    架

    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
     usual
    -0.08
     mahi
    -0.07
    ייש
    -0.07
    ater
    -0.07
     endothelial
    -0.07
     barbar
    -0.07
     baseline
    -0.07
     autore
    -0.07
     изготов
    -0.07
     catalytic
    -0.07
    POSITIVE LOGITS
     taxonomy
    0.12
    taxonomy
    0.12
    结构
    0.11
    _structure
    0.10
    Hierarchy
    0.10
     árvore
    0.10
     hierarchy
    0.10
     구조
    0.10
     hier
    0.09
     estrutura
    0.09
    Activations Density 0.010%

    No Known Activations