© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102373
    Prev
    Next
    INDEX
    Explanations

    and or or

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ،
    -0.14
    ↵↵　↵
    -0.12
    、名無し
    -0.12
     ՝
    -0.12
    ‌,
    -0.12
    、その
    -0.12
    ,天天
    -0.12
     Ayrıca
    -0.12
     იმდენ
    -0.12
     ნების
    -0.12
    POSITIVE LOGITS
     code
    0.08
    or
    0.08
     plan
    0.07
     class
    0.07
     function
    0.07
     intuition
    0.07
     purpose
    0.07
    acles
    0.07
     folklore
    0.07
     slang
    0.07
    Activations Density 0.107%

    No Known Activations