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. 104042
    Prev
    Next
    INDEX
    Explanations

    random numbers

    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
     Render
    -0.08
     Smart
    -0.08
    ibil
    -0.07
    (Render
    -0.07
    .shader
    -0.07
     feat
    -0.07
    Render
    -0.07
    .Infof
    -0.07
     il
    -0.07
     rendering
    -0.07
    POSITIVE LOGITS
     interpreting
    0.09
     randomly
    0.09
    随机
    0.09
     roulette
    0.09
     fscanf
    0.09
     wille
    0.09
    亂
    0.09
    的彩票
    0.09
    	random
    0.09
    (random
    0.09
    Activations Density 0.004%

    No Known Activations