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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11842
    Prev
    Next
    INDEX
    Explanations

    draught

    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
     constructive
    -0.10
     Cai
    -0.09
    赚钱
    -0.08
    �
    -0.08
    里面
    -0.08
    建
    -0.08
    续
    -0.08
    ható
    -0.08
    现实
    -0.07
     voim
    -0.07
    POSITIVE LOGITS
    bcrypt
    0.08
     owing
    0.08
     знаком
    0.08
    .live
    0.08
     chuck
    0.08
    pipe
    0.07
    zera
    0.07
    soil
    0.07
     presso
    0.07
    _pipe
    0.07
    Activations Density 0.006%

    No Known Activations