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. 120351
    Prev
    Next
    INDEX
    Explanations

    1

    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
     تج
    -0.09
     ap
    -0.08
     crack
    -0.07
     parsing
    -0.07
    owing
    -0.07
     sh
    -0.07
     통한
    -0.07
     staging
    -0.07
     Hans
    -0.07
     producing
    -0.07
    POSITIVE LOGITS
     subordin
    0.08
    此前
    0.08
    0.08
     多
    0.08
     首
    0.08
     此
    0.08
    IAM
    0.07
     注意
    0.07
     于
    0.07
     rigu
    0.07
    Activations Density 0.016%

    No Known Activations