© 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. 47904
    Prev
    Next
    INDEX
    Explanations

    instructions, explanations

    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
    ೈ
    -0.09
    Dear
    -0.08
    ಾತ
    -0.08
    ಾಜ
    -0.07
     whatsoever
    -0.07
    ್ಟ್
    -0.07
    -0.07
     alls
    -0.07
    î
    -0.07
    /or
    -0.07
    POSITIVE LOGITS
     उदाहरण
    0.08
    赌场
    0.08
    Pakistan
    0.08
     पाकिस्तान
    0.08
    ])).
    0.08
     FIFA
    0.08
    icione
    0.08
     Пот
    0.08
     필요
    0.08
     cranberry
    0.08
    Activations Density 0.393%
    No Known Activations