Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 12956
    Prev
    Next
    INDEX
    Explanations

    Jordan

    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
    Glob
    -0.08
     Spa
    -0.08
    SPA
    -0.08
     digestion
    -0.08
     Ministers
    -0.08
    PIO
    -0.08
     ministers
    -0.08
    Spa
    -0.08
     vem
    -0.07
    _RPC
    -0.07
    POSITIVE LOGITS
    drv
    0.09
     homework
    0.09
    高中
    0.08
     drv
    0.08
    雪
    0.08
     perpendicular
    0.08
    ianz
    0.07
     ચાર
    0.07
    /business
    0.07
    ashion
    0.07
    Activations Density 0.002%

    No Known Activations