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. 23-RESID-POST-AA
    6. 130916
    Prev
    Next
    INDEX
    Explanations

    say "driver"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PET
    -0.09
     polyester
    -0.09
     salle
    -0.08
     Polyester
    -0.08
     सभा
    -0.08
     Palazzo
    -0.08
     necklace
    -0.08
     sqm
    -0.08
     necklaces
    -0.08
     festas
    -0.08
    POSITIVE LOGITS
     driver
    0.61
    	driver
    0.57
    Driver
    0.57
     drivers
    0.56
    (driver
    0.56
    _driver
    0.56
     ഡ്ര
    0.56
     Driver
    0.55
     драй
    0.55
    driver
    0.55
    Activations Density 0.099%

    No Known Activations