© 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. 47608
    Prev
    Next
    INDEX
    Explanations

    Words for test

    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
     Gespräch
    -0.09
     discutir
    -0.08
     разговор
    -0.08
     మాట్ల
    -0.08
     hablamos
    -0.08
     לדבר
    -0.08
    umanité
    -0.08
    ైత
    -0.08
    atisfactory
    -0.08
    claration
    -0.08
    POSITIVE LOGITS
    测试
    0.23
     testing
    0.22
     परीक्षण
    0.21
    Testing
    0.21
     테스트
    0.21
     test
    0.20
    Test
    0.20
     testen
    0.20
     పరీక్ష
    0.20
     ಪರೀಕ್ಷ
    0.20
    Activations Density 0.090%

    No Known Activations