© 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. 94883
    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
     absolument
    -0.09
    الات
    -0.08
    și
    -0.08
     suoi
    -0.07
    Dato
    -0.07
     Kashmir
    -0.07
     développement
    -0.07
    排行榜
    -0.07
    lant
    -0.07
    كية
    -0.07
    POSITIVE LOGITS
     hig
    0.09
     cumbersome
    0.08
     Limits
    0.08
     হ
    0.08
     inadequate
    0.07
    _limits
    0.07
     ',
    0.07
     से
    0.07
     воб
    0.07
     inadequ
    0.07
    Activations Density 0.009%

    No Known Activations