Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 88225
    Prev
    Next
    INDEX
    Explanations

    line or phrase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ��
    -0.08
    ушки
    -0.07
     sor
    -0.07
    .Se
    -0.07
     jour
    -0.07
     необходимых
    -0.07
    amatan
    -0.07
     pot
    -0.07
     copper
    -0.07
     Champion
    -0.07
    POSITIVE LOGITS
     부분
    0.10
    句
    0.09
     हिस्सा
    0.09
     অংশ
    0.09
     stanza
    0.09
    一句
    0.08
     portion
    0.08
    描
    0.08
     فلسطين
    0.08
    ago
    0.08
    Activations Density 0.021%

    No Known Activations