© 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. 49179
    Prev
    Next
    INDEX
    Explanations

    say "的"

    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
     &=
    -0.09
    」は
    -0.09
     থাকে
    -0.09
     have
    -0.08
    は
    -0.08
     showed
    -0.08
    appropr
    -0.08
     ಇದು
    -0.08
     relate
    -0.07
     were
    -0.07
    POSITIVE LOGITS
    的一
    0.21
    的重要
    0.21
     egyik
    0.20
     অন্যতম
    0.18
    不可
    0.18
    最
    0.18
     સૌથી
    0.16
     가장
    0.15
     ഏറ്റവും
    0.15
     সবচ
    0.15
    Activations Density 0.044%

    No Known Activations