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. 30642
    Prev
    Next
    INDEX
    Explanations

    (

    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
     Eventually
    -0.08
     Victorian
    -0.08
     ஒன்று
    -0.07
     filings
    -0.07
     کمی
    -0.07
     USC
    -0.07
     PLC
    -0.07
     démarches
    -0.07
     SBA
    -0.07
    ippers
    -0.07
    POSITIVE LOGITS
    �
    0.10
     gel
    0.08
    														
    0.08
    oni
    0.08
    gel
    0.08
    �
    0.08
     sling
    0.07
    柱
    0.07
    ��
    0.07
     ಅರ
    0.07
    Activations Density 0.004%

    No Known Activations