© 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. 695
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Saturday
    -0.09
     busiest
    -0.08
     sábado
    -0.08
     ót
    -0.08
     Saturday
    -0.08
    ಾಟ್
    -0.08
    yramid
    -0.08
     Superintendent
    -0.08
     Sask
    -0.08
     extremos
    -0.08
    POSITIVE LOGITS
     comp
    0.08
    694
    0.07
    盾
    0.07
     Ł
    0.07
     lettuce
    0.07
     locus
    0.07
     metabolism
    0.07
    力量
    0.07
     �
    0.07
     conduite
    0.07
    Activations Density 0.024%

    No Known Activations