© 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. 8124
    Prev
    Next
    INDEX
    Explanations

    "based" and foundations

    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
    >>>
    -0.08
     yaxın
    -0.08
    Domin
    -0.08
    �
    -0.08
    Beauty
    -0.08
     rectify
    -0.08
    ║
    -0.07
     Santo
    -0.07
     >>>
    -0.07
    █
    -0.07
    POSITIVE LOGITS
     principles
    0.11
     gebaseerd
    0.10
     आधार
    0.10
     ভিত্ত
    0.10
     أساس
    0.09
     basiert
    0.09
     основе
    0.09
     חל
    0.09
     आधारित
    0.09
     આધાર
    0.09
    Activations Density 0.089%

    No Known Activations