© 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. 24682
    Prev
    Next
    INDEX
    Explanations

    dehydration

    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
    ution
    -0.09
    沿
    -0.08
    ায়
    -0.08
    .
↵
    -0.08
    ).
↵
    -0.08
    ায়
    -0.08
     generators
    -0.08
     booming
    -0.08
    特色
    -0.08
     soweit
    -0.07
    POSITIVE LOGITS
     Jak
    0.08
     poursu
    0.08
     inaccurate
    0.08
     suffered
    0.08
     Valuable
    0.08
     दुख
    0.08
     incurred
    0.08
     irrit
    0.08
     खराब
    0.07
     atte
    0.07
    Activations Density 0.004%

    No Known Activations