© 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. 11-RESID-POST-AA
    11. 29069
    Prev
    Next
    INDEX
    Explanations

    имени

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     व्यवस्थ
    -0.08
     Barb
    -0.08
     নির্বাচ
    -0.08
    -part
    -0.08
    -performing
    -0.08
    stub
    -0.07
     გეგმ
    -0.07
    _bill
    -0.07
     hygien
    -0.07
    niques
    -0.07
    POSITIVE LOGITS
     empe
    0.08
     vient
    0.07
     Karena
    0.07
     чувство
    0.07
     Feed
    0.07
     ومح
    0.07
    ดู
    0.07
     wiederum
    0.07
     дни
    0.07
     дней
    0.07
    Activations Density 0.001%

    No Known Activations