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. 43702
    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
     panoramic
    -0.07
     positions
    -0.07
    Continuation
    -0.07
     continuation
    -0.07
    ांना
    -0.07
    (now
    -0.07
     சம
    -0.07
    Beyond
    -0.07
    ="$
    -0.06
    Hu
    -0.06
    POSITIVE LOGITS
    赌场
    0.09
     pob
    0.08
     Dam
    0.08
     বিধ
    0.08
    /url
    0.08
     переп
    0.08
     jes
    0.08
     ধ
    0.07
     Arun
    0.07
     прок
    0.07
    Activations Density 0.052%

    No Known Activations