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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12910
    Prev
    Next
    INDEX
    Explanations

    Pride and Prejudice

    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
     retinal
    -0.09
     outages
    -0.08
    Tau
    -0.08
    Tapped
    -0.08
     emergency
    -0.08
     plas
    -0.08
     Tau
    -0.08
     FIR
    -0.08
    akama
    -0.08
     hvad
    -0.08
    POSITIVE LOGITS
     cottage
    0.10
     Cottage
    0.10
     Austen
    0.09
     charme
    0.09
     charming
    0.09
    Classic
    0.09
    嫁
    0.09
     manor
    0.08
    经典
    0.08
     古
    0.08
    Activations Density 0.007%

    No Known Activations