© 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. 651
    Prev
    Next
    INDEX
    Explanations

    within

    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
     कि
    -0.08
    Pot
    -0.08
     मॉडल
    -0.07
     ब्य
    -0.07
     मॉ
    -0.07
    /models
    -0.07
     únicas
    -0.07
    Unique
    -0.07
     unik
    -0.07
    SSR
    -0.07
    POSITIVE LOGITS
     interne
    0.08
     manje
    0.08
    	internal
    0.08
     maupun
    0.08
     internos
    0.08
     internal
    0.08
     giữa
    0.08
     Industrie
    0.08
    和平
    0.08
     interior
    0.08
    Activations Density 0.013%

    No Known Activations