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. 97986
    Prev
    Next
    INDEX
    Explanations

    Special characters for code

    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
     organically
    -0.08
     conceived
    -0.07
    ுமே
    -0.07
     geschreven
    -0.07
    (which
    -0.07
     authored
    -0.07
     surfaced
    -0.07
    怎么
    -0.07
     penned
    -0.07
     fashioned
    -0.07
    POSITIVE LOGITS
     ";"
    0.27
     commas
    0.27
     ":"
    0.26
     ':'
    0.26
     trailing
    0.25
     '='
    0.25
     "="
    0.25
     "/"
    0.25
     ','
    0.24
     '#'
    0.24
    Activations Density 0.074%

    No Known Activations