© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 50708
    Prev
    Next
    INDEX
    Explanations

    say "の"

    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
    적으로
    -0.13
     yén
    -0.13
     bahwa
    -0.11
    적인
    -0.11
     대해
    -0.10
    们
    -0.10
     bahawa
    -0.10
    서는
    -0.10
     रुपमा
    -0.10
    해서
    -0.09
    POSITIVE LOGITS
    の
    0.55
    의
    0.42
     の
    0.39
    のお
    0.29
     యొక్క
    0.27
    യുടെ
    0.27
    の商品
    0.27
    च्या
    0.27
    の記事
    0.25
    ના
    0.25
    Activations Density 0.024%

    No Known Activations