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. 19231
    Prev
    Next
    INDEX
    Explanations

    international data transfer

    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
     trži
    -0.09
     revisit
    -0.08
     অভি�
    -0.08
     tâ
    -0.08
    Qualified
    -0.08
    'équ
    -0.08
    市場
    -0.07
     pastoral
    -0.07
     plural
    -0.07
    <TKey
    -0.07
    POSITIVE LOGITS
     uploading
    0.10
     подачи
    0.09
    cryption
    0.08
    iening
    0.08
    脸
    0.08
    下载
    0.08
    upload
    0.08
     transferencia
    0.07
     韩国
    0.07
    aisseur
    0.07
    Activations Density 0.002%

    No Known Activations