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. 42439
    Prev
    Next
    INDEX
    Explanations

    gratitude

    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
    /linux
    -0.08
     linux
    -0.08
    そこ
    -0.08
     Kag
    -0.07
     unfortunately
    -0.07
     Zh
    -0.07
     mem
    -0.07
     ഇംഗ്ല
    -0.07
     contund
    -0.07
     exacte
    -0.07
    POSITIVE LOGITS
     fosters
    0.09
     stimulates
    0.08
     сниз
    0.08
    otherapy
    0.08
     multit
    0.08
     Effect
    0.08
     يؤدي
    0.08
     अपन
    0.08
     прошло
    0.08
    性生活
    0.07
    Activations Density 0.031%

    No Known Activations