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. 88216
    Prev
    Next
    INDEX
    Explanations

    ist

    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
     disso
    -0.08
    hire
    -0.07
     ama
    -0.07
     mâ
    -0.07
    alz
    -0.07
    Arthur
    -0.07
    Gee
    -0.07
     inex
    -0.07
    射
    -0.07
    Gap
    -0.07
    POSITIVE LOGITS
     fo
    0.08
     paving
    0.08
    0.08
    -minded
    0.08
     paved
    0.07
     notions
    0.07
     взгляд
    0.07
     направ
    0.07
    0.07
     Gö
    0.07
    Activations Density 0.059%

    No Known Activations