© 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. 11-RESID-POST-AA
    11. 64840
    Prev
    Next
    INDEX
    Explanations

    Period

    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
    资本
    -0.11
    -envelope
    -0.09
     terro
    -0.09
     aposent
    -0.09
     సందర్భంగా
    -0.09
    ాగ
    -0.08
    寿
    -0.08
    మైన
    -0.08
     garments
    -0.08
    ాం�
    -0.08
    POSITIVE LOGITS
     anxiety
    0.09
     eyewitness
    0.08
    Search
    0.08
     fever
    0.08
     ಹೆಚ್ಚು
    0.08
     anxious
    0.08
    搜尋
    0.08
     proactive
    0.08
     Searching
    0.08
    Searching
    0.08
    Activations Density 0.042%

    No Known Activations