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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 113079
    Prev
    Next
    INDEX
    Explanations

    airway/breathing difficulty

    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
    isdiction
    -0.08
     uru
    -0.08
     spoil
    -0.07
    /ex
    -0.07
     fragments
    -0.07
     Ausland
    -0.07
     tune
    -0.07
    asiya
    -0.07
    الى
    -0.07
    论
    -0.07
    POSITIVE LOGITS
     airway
    0.11
     throat
    0.10
    fet
    0.10
     cervical
    0.09
     Speech
    0.09
     Airways
    0.08
    -danger
    0.08
    ekomst
    0.08
     cerv
    0.08
    jobb
    0.08
    Activations Density 0.006%

    No Known Activations