© 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 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. 50222
    Prev
    Next
    INDEX
    Explanations

    say "化"

    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
     entirety
    -0.07
     להיות
    -0.07
    181
    -0.07
     být
    -0.07
     શકે
    -0.07
     volgende
    -0.07
    _original
    -0.07
     Anspruch
    -0.07
     agarr
    -0.07
     être
    -0.07
    POSITIVE LOGITS
    化
    0.70
     化
    0.56
    화
    0.50
    화를
    0.47
    ization
    0.43
     hóa
    0.42
    ized
    0.36
    izing
    0.35
    isation
    0.33
    izations
    0.33
    Activations Density 0.080%

    No Known Activations