Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90028
    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
     :)
    -0.09
    ಹ
    -0.08
    �
    -0.08
     ·
    -0.08
    ად
    -0.08
     pencil
    -0.07
     essa
    -0.07
    geries
    -0.07
     وعلى
    -0.07
    宜
    -0.07
    POSITIVE LOGITS
     biotechnology
    0.09
     Lastly
    0.09
     网络
    0.08
     Musée
    0.08
     Evergreen
    0.08
     Aging
    0.08
     biotech
    0.08
     agrícolas
    0.08
     Pri
    0.08
     Greenpeace
    0.08
    Activations Density 0.029%

    No Known Activations