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

    Neuronpedia

    APICircuit 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. 43901
    Prev
    Next
    INDEX
    Explanations

    weapon

    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
     gepland
    -0.09
     Venez
    -0.08
    凝
    -0.08
     executed
    -0.08
     cohes
    -0.08
     volto
    -0.08
     uitgevoerd
    -0.08
     vun
    -0.08
     carton
    -0.08
    xmlns
    -0.08
    POSITIVE LOGITS
     ورو
    0.08
    거리
    0.08
     وع
    0.07
    .weapon
    0.07
    halter
    0.07
     arsenal
    0.07
    ателю
    0.07
    殊
    0.07
    েন
    0.07
    0.07
    Activations Density 0.006%

    No Known Activations