© 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. 78506
    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
     kial
    -0.08
    处理
    -0.08
    创业
    -0.08
    escence
    -0.08
    疗
    -0.07
    ాల
    -0.07
     Assault
    -0.07
     Dressing
    -0.07
     Infantil
    -0.07
    esity
    -0.07
    POSITIVE LOGITS
     pies
    0.08
     alleg
    0.08
     adet
    0.08
     coats
    0.08
     rug
    0.08
    Visual
    0.07
     scrib
    0.07
     teal
    0.07
    ثل
    0.07
     विद्य
    0.07
    Activations Density 0.002%

    No Known Activations