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. 54308
    Prev
    Next
    INDEX
    Explanations

    meningitis

    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
    fulness
    -0.08
     kitchen
    -0.07
     lagi
    -0.07
     kodi
    -0.07
    JA
    -0.07
    TURE
    -0.07
     Matrix
    -0.07
    /ag
    -0.07
     ingenu
    -0.07
     footh
    -0.07
    POSITIVE LOGITS
    icide
    0.09
    вычай
    0.08
    ський
    0.08
    icides
    0.08
     transmissão
    0.08
     tomb
    0.08
     السود
    0.07
    923
    0.07
    _sdk
    0.07
    ամ
    0.07
    Activations Density 0.001%

    No Known Activations