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. 77548
    Prev
    Next
    INDEX
    Explanations

    Toll-free phone numbers

    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
     observational
    -0.08
    ell
    -0.08
     ell
    -0.07
     esp
    -0.07
    卧
    -0.07
     �
    -0.07
    模
    -0.07
    nius
    -0.07
    elite
    -0.07
     mistress
    -0.07
    POSITIVE LOGITS
     cola
    0.08
     Unser
    0.08
     Successfully
    0.08
     kli
    0.08
     Buick
    0.08
     Kul
    0.08
     zacht
    0.08
     swa
    0.07
     thương
    0.07
     restarting
    0.07
    Activations Density 0.005%

    No Known Activations