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. 54221
    Prev
    Next
    INDEX
    Explanations

    refund

    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
    .payload
    -0.08
    �
    -0.07
    ##_
    -0.07
     Owl
    -0.07
     grooves
    -0.07
     thousand
    -0.07
     signaling
    -0.07
     geheim
    -0.07
     außer
    -0.07
     revel
    -0.07
    POSITIVE LOGITS
     owed
    0.08
     receipt
    0.08
    金额
    0.08
    退款
    0.08
     placebo
    0.08
    Exact
    0.08
    行政
    0.08
    받
    0.08
    attention
    0.08
    政策
    0.08
    Activations Density 0.005%

    No Known Activations