© 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. 95065
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Bertrand
    -0.09
     وارد
    -0.08
     ubiquitous
    -0.08
     Nieder
    -0.08
    	elem
    -0.08
     перевоз
    -0.08
     pioneering
    -0.08
     Ribe
    -0.08
    credential
    -0.08
    开展
    -0.08
    POSITIVE LOGITS
     presets
    0.09
     GAN
    0.09
     upscale
    0.09
     genere
    0.09
     GPT
    0.09
    512
    0.08
    生成
    0.08
     Generates
    0.08
     CUDA
    0.08
     Save
    0.07
    Activations Density 0.008%

    No Known Activations