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. 98354
    Prev
    Next
    INDEX
    Explanations

    say "class" and "def"

    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
     absorbs
    -0.09
     throws
    -0.09
     absorbing
    -0.08
     sequences
    -0.08
    .UIManager
    -0.08
    าห
    -0.08
    .starts
    -0.08
     makes
    -0.08
     sums
    -0.08
    สู
    -0.08
    POSITIVE LOGITS
     authorize
    0.12
    authorize
    0.10
     skip
    0.10
     params
    0.09
     respond
    0.09
     Policies
    0.09
     expire
    0.08
    params
    0.08
     GDPR
    0.08
    Authorize
    0.08
    Activations Density 0.000%

    No Known Activations