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. 75903
    Prev
    Next
    INDEX
    Explanations

    electrical substations

    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
     indie
    -0.10
     scent
    -0.10
     foodie
    -0.09
     disadvantaged
    -0.09
    bait
    -0.09
     procrast
    -0.08
    巧
    -0.08
     NIH
    -0.08
     Indie
    -0.08
     Tumblr
    -0.08
    POSITIVE LOGITS
     Offshore
    0.10
     offshore
    0.10
     outages
    0.10
     armored
    0.09
     बिजली
    0.09
    施工
    0.09
     workstation
    0.08
     อาคาร
    0.08
     Voltage
    0.08
     STF
    0.08
    Activations Density 0.017%

    No Known Activations