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. 15-RESID-POST-AA
    6. 19232
    Prev
    Next
    INDEX
    Explanations

    curl

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gradu
    -0.09
    assembl
    -0.07
     markup
    -0.07
    ynchronize
    -0.07
    সং
    -0.07
     synchronize
    -0.07
     decentral
    -0.07
     simplex
    -0.07
     sek
    -0.07
     berarti
    -0.07
    POSITIVE LOGITS
    Around
    0.11
     around
    0.10
    -haired
    0.10
     вокруг
    0.09
     alrededor
    0.09
     Around
    0.08
     Yorkshire
    0.08
     حول
    0.08
     torno
    0.08
     autour
    0.08
    Activations Density 0.005%

    No Known Activations