© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91363
    Prev
    Next
    INDEX
    Explanations

    Multiple languages and business

    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
     cages
    -0.08
    pop
    -0.08
     limestone
    -0.08
     Nebraska
    -0.07
    еса
    -0.07
     속
    -0.07
     litter
    -0.07
    ès
    -0.07
     Briggs
    -0.07
     pel
    -0.07
    POSITIVE LOGITS
     namens
    0.08
    >You
    0.07
     niedrig
    0.07
     Condition
    0.07
     scholar
    0.07
    (beta
    0.07
     kleur
    0.07
    >No
    0.07
     плат
    0.07
     Sadly
    0.07
    Activations Density 0.026%

    No Known Activations