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. 15-RESID-POST-AA
    6. 19430
    Prev
    Next
    INDEX
    Explanations

    main

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     élev
    -0.08
     kız
    -0.08
     notion
    -0.08
     daug
    -0.08
     whereas
    -0.08
    ירות
    -0.08
     assumption
    -0.08
     dichas
    -0.08
     stationary
    -0.07
     élevé
    -0.07
    POSITIVE LOGITS
    (){↵
    0.13
    (){↵↵
    0.13
    ()
    0.13
    ():↵
    0.12
     {↵↵
    0.11
    (argv
    0.11
     {↵
    0.10
    ()↵
    0.10
    (figsize
    0.10
    ():↵↵
    0.10
    Activations Density 0.002%

    No Known Activations