© 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. 23-RESID-POST-AA
    11. 5472
    Prev
    Next
    INDEX
    Explanations

    Warriors and tribes

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prefeitura
    -0.09
     Reactor
    -0.09
     وزارة
    -0.09
     usine
    -0.09
     textbooks
    -0.09
     وزارت
    -0.08
     Министер
    -0.08
    办公室
    -0.08
     Ministry
    -0.08
    国务院
    -0.08
    POSITIVE LOGITS
     warrior
    0.22
     warriors
    0.21
     tribal
    0.20
     tribes
    0.19
     raids
    0.19
     উপজ
    0.18
     tribe
    0.18
     cavalry
    0.18
     nom
    0.17
     horseback
    0.16
    Activations Density 0.063%

    No Known Activations