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. 43635
    Prev
    Next
    INDEX
    Explanations

    Composition

    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
    玛
    -0.08
     dokon
    -0.08
     хар
    -0.08
     vell
    -0.08
    									
    -0.08
     modeled
    -0.08
     Madh
    -0.07
     DEL
    -0.07
     মাম
    -0.07
     kerran
    -0.07
    POSITIVE LOGITS
    ,Object
    0.09
    ="{
    0.08
    bene
    0.08
    <Object
    0.08
     सारी
    0.07
    JS
    0.07
    Graph
    0.07
     Speak
    0.07
    graphql
    0.07
     user's
    0.07
    Activations Density 0.001%

    No Known Activations