Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56266
    Prev
    Next
    INDEX
    Explanations

    say

    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
    seguir
    -0.07
     anybody
    -0.07
    pero
    -0.07
     pelanggan
    -0.07
    segu
    -0.07
    ble
    -0.07
    paa
    -0.07
     anytime
    -0.07
    ettle
    -0.07
    Fantasy
    -0.07
    POSITIVE LOGITS
     جہ
    0.08
     lệ
    0.08
    ಂಭ
    0.07
     obl
    0.07
     obscure
    0.07
     као
    0.07
     تخت
    0.07
     kao
    0.07
     склад
    0.07
    fc
    0.07
    Activations Density 0.003%

    No Known Activations