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. 106029
    Prev
    Next
    INDEX
    Explanations

    Webpage excerpts

    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
    urray
    -0.09
     flavor
    -0.08
     attain
    -0.08
     news
    -0.07
     Flavor
    -0.07
     zetten
    -0.07
     Sal
    -0.07
    jski
    -0.07
     season
    -0.07
     uncover
    -0.07
    POSITIVE LOGITS
    _Static
    0.08
     人
    0.08
    ろしく
    0.08
     ಮಂದ
    0.08
     真人
    0.08
     Leuten
    0.08
    _UClass
    0.08
     女性
    0.07
    \htdocs
    0.07
     HOWEVER
    0.07
    Activations Density 1.312%

    No Known Activations