© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 54681
    Prev
    Next
    INDEX
    Explanations

    beginnings

    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
     beforehand
    -0.08
     particulate
    -0.08
    lıklı
    -0.08
    ready
    -0.08
     aanu
    -0.07
     Br
    -0.07
     xuống
    -0.07
     MW
    -0.07
    ौल
    -0.07
    नीय
    -0.07
    POSITIVE LOGITS
     humilde
    0.09
    始
    0.08
     começaram
    0.08
     gradually
    0.08
     ঘটে
    0.08
     começou
    0.08
     langzaam
    0.08
    以来
    0.08
     pove
    0.08
    .tel
    0.08
    Activations Density 0.058%

    No Known Activations