© 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. 26459
    Prev
    Next
    INDEX
    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
     यी
    -0.08
     gauge
    -0.08
    Gauge
    -0.08
    _y
    -0.07
    耀
    -0.07
    _DE
    -0.07
    _w
    -0.07
    赶
    -0.07
    اعة
    -0.07
    _login
    -0.07
    POSITIVE LOGITS
     porn
    0.08
    赔率
    0.08
     отношения
    0.08
    ագետ
    0.08
     sûre
    0.08
     العلاقة
    0.08
     powod
    0.08
     αποτε
    0.08
     Rek
    0.08
     veilige
    0.08
    Activations Density 0.001%

    No Known Activations