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. 98592
    Prev
    Next
    INDEX
    Explanations

    во

    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
    żi
    -0.10
    çăo
    -0.09
    ї
    -0.09
    alı
    -0.09
    żli
    -0.09
    .Fill
    -0.08
    θή
    -0.08
    ýanyň
    -0.08
    ýasynyň
    -0.08
    wenn
    -0.08
    POSITIVE LOGITS
    ев
    0.09
    m
    0.08
    енным
    0.07
     num
    0.07
    оруж
    0.07
    енному
    0.07
     male
    0.07
    енными
    0.07
    isty
    0.07
    енное
    0.07
    Activations Density 0.001%

    No Known Activations