© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 95588
    Prev
    Next
    INDEX
    Explanations

    Content creation and publishing

    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
     tabu
    -0.08
    	table
    -0.08
    询
    -0.07
     strstr
    -0.07
     union
    -0.07
     inequalities
    -0.07
    �
    -0.07
     vraagt
    -0.07
    	Table
    -0.07
     Union
    -0.07
    POSITIVE LOGITS
     регулярно
    0.13
     regularmente
    0.13
     réguli
    0.12
     cadence
    0.12
     régulièrement
    0.11
     नियमित
    0.11
     regelmäßig
    0.10
     regelmäß
    0.10
    发布时间
    0.10
    发布
    0.10
    Activations Density 0.038%

    No Known Activations