© 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. 47490
    Prev
    Next
    INDEX
    Explanations

    Е

    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
    ого
    -0.08
     suoi
    -0.08
     такие
    -0.08
    concile
    -0.08
    лаго
    -0.08
     очевид
    -0.07
     الاتجاه
    -0.07
     amandla
    -0.07
     meilleur
    -0.07
     meilleure
    -0.07
    POSITIVE LOGITS
    idin
    0.08
     WON
    0.08
    wid
    0.08
    adt
    0.08
    idan
    0.08
    edor
    0.08
    idas
    0.07
     dövlət
    0.07
    miss
    0.07
    /tab
    0.07
    Activations Density 0.002%

    No Known Activations