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. 8957
    Prev
    Next
    INDEX
    Explanations

    ~

    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
     grat
    -0.08
     والم
    -0.08
     तसे
    -0.08
    /jquery
    -0.08
    敗
    -0.07
     سرگر
    -0.07
    رداری
    -0.07
     etiam
    -0.07
     الذين
    -0.07
     همچنین
    -0.07
    POSITIVE LOGITS
    变化
    0.08
    ોર્મ
    0.08
    Clk
    0.08
    ’d
    0.07
    岁的
    0.07
     Bezug
    0.07
     Gabriel
    0.07
    Toutes
    0.07
    Age
    0.07
    是什么意思
    0.07
    Activations Density 25.664%

    No Known Activations