© 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. 19-RESID-POST-AA
    11. 102387
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     finest
    -0.08
     welt
    -0.08
     слишком
    -0.08
     insgesamt
    -0.07
     troppo
    -0.07
    比
    -0.07
     too
    -0.07
     самые
    -0.07
    โน
    -0.07
     tenga
    -0.07
    POSITIVE LOGITS
     hlok
    0.09
     phahameng
    0.09
     хайр
    0.09
    »,-
    0.09
     أصبحت
    0.09
    ýän
    0.09
     derejes
    0.09
     redirected
    0.09
     méthodes
    0.09
     միջոցով
    0.09
    Activations Density 0.005%

    No Known Activations