© 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. 579
    Prev
    Next
    INDEX
    Explanations

    sales or services

    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
     spécialis
    -0.08
     Specialized
    -0.07
    -0.07
     यूर
    -0.07
     संश
    -0.07
     imperial
    -0.07
     municipal
    -0.07
     cámara
    -0.07
    metic
    -0.07
    特殊
    -0.07
    POSITIVE LOGITS
    -oriented
    0.08
     Greg
    0.08
     Shuffle
    0.08
     Fais
    0.08
     snar
    0.08
     перей
    0.07
     Pokemon
    0.07
     رجل
    0.07
     troch
    0.07
    .Message
    0.07
    Activations Density 0.067%
    No Known Activations