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. 113799
    Prev
    Next
    INDEX
    Explanations

    Walmart

    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
    自由
    -0.08
     Gilles
    -0.08
     designation
    -0.08
    年以上
    -0.08
    随
    -0.07
     brake
    -0.07
    輪
    -0.07
     repertoire
    -0.07
     determin
    -0.07
    但是
    -0.07
    POSITIVE LOGITS
     Walmart
    0.10
     Sunn
    0.09
     mog
    0.08
     Corte
    0.08
     oč
    0.08
     sle
    0.08
     Oral
    0.08
    .Mobile
    0.08
     merchandise
    0.08
    עצ
    0.08
    Activations Density 0.007%

    No Known Activations