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. 53862
    Prev
    Next
    INDEX
    Explanations

    draw

    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
     kompat
    -0.08
     Toss
    -0.08
    .Verify
    -0.08
     Gorgeous
    -0.08
    acific
    -0.08
    AXB
    -0.08
    .Inject
    -0.08
     Estou
    -0.07
     Pim
    -0.07
    जार
    -0.07
    POSITIVE LOGITS
     gated
    0.09
     ventre
    0.08
    -cent
    0.08
     شف
    0.08
     phased
    0.08
     phantom
    0.08
     vault
    0.07
     Lind
    0.07
     drawers
    0.07
    Fullscreen
    0.07
    Activations Density 0.002%

    No Known Activations