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. 101529
    Prev
    Next
    INDEX
    Explanations

    differential

    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
    Moderator
    -0.08
    (Pro
    -0.08
     restructure
    -0.08
    Messenger
    -0.08
    [,]
    -0.07
     другу
    -0.07
     коллектив
    -0.07
    Labor
    -0.07
    /editor
    -0.07
    staat
    -0.07
    POSITIVE LOGITS
     digits
    0.08
    үгүн
    0.08
    џ
    0.08
     Jazz
    0.08
    iex
    0.07
    mu
    0.07
    glib
    0.07
    plist
    0.07
     gim
    0.07
    μ
    0.07
    Activations Density 0.001%

    No Known Activations