© 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. 103313
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
     번째
    -0.10
    atasets
    -0.09
    авіта
    -0.09
     그대로
    -0.09
     تريد
    -0.09
    しく
    -0.08
     dafür
    -0.08
    נסה
    -0.08
    yses
    -0.08
    يم
    -0.08
    POSITIVE LOGITS
    -item
    0.09
     totalt
    0.09
     тщательно
    0.08
    -items
    0.08
     consolidated
    0.08
     pcs
    0.08
    ,etc
    0.08
    /week
    0.08
    /core
    0.08
     разно
    0.08
    Activations Density 0.029%

    No Known Activations