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. 55932
    Prev
    Next
    INDEX
    Explanations

    Balancing flavors in food

    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
     founders
    -0.08
     founder
    -0.08
    oude
    -0.08
     gegründet
    -0.07
     znal
    -0.07
     vertegenwoord
    -0.07
     deme
    -0.07
    遵
    -0.07
    .pres
    -0.07
    ,Http
    -0.07
    POSITIVE LOGITS
     merch
    0.10
     Melanie
    0.09
     merchandising
    0.09
     אות
    0.08
     merchandise
    0.08
    Cancel
    0.08
     ///↵
    0.08
     thanh
    0.08
    Compl
    0.08
    万円
    0.08
    Activations Density 0.009%

    No Known Activations