© 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. 96328
    Prev
    Next
    INDEX
    Explanations

    diaspora

    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
     regionale
    -0.08
     พระ
    -0.08
     trocken
    -0.08
    裸体
    -0.08
     الوطني
    -0.08
     阜
    -0.08
    	local
    -0.07
     государственной
    -0.07
     landelijke
    -0.07
    动物
    -0.07
    POSITIVE LOGITS
     diaspora
    0.28
     expatri
    0.25
     immigrant
    0.24
     dias
    0.24
     immigrants
    0.23
     emigr
    0.22
     эми
    0.20
    Dias
    0.20
     inmigr
    0.20
     immigr
    0.19
    Activations Density 0.076%

    No Known Activations