© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 99478
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     Cyrus
    -0.09
     kjent
    -0.08
    CAD
    -0.07
    CAP
    -0.07
    Bank
    -0.07
     가치
    -0.07
     هنوز
    -0.07
     CAP
    -0.07
    /problem
    -0.07
    Simulator
    -0.07
    POSITIVE LOGITS
     spaced
    0.09
     concise
    0.09
     möglichst
    0.09
     commas
    0.09
     preferably
    0.09
     формат
    0.08
     प्रार
    0.08
     victoria
    0.08
     ideally
    0.08
    taf
    0.08
    Activations Density 0.007%

    No Known Activations