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

    Neuronpedia

    Jacobian LensNEW
    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. 69433
    Prev
    Next
    INDEX
    Explanations

    disclaimers

    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
    vergleich
    -0.07
    potential
    -0.07
     Comparative
    -0.07
     Comparison
    -0.07
    pur
    -0.07
    purple
    -0.07
    Potential
    -0.07
    onj
    -0.07
    રુ
    -0.07
    length
    -0.07
    POSITIVE LOGITS
     strives
    0.13
     bemü
    0.10
     strive
    0.10
    しております
    0.09
     striving
    0.09
     möglichst
    0.08
     પ્રય
    0.08
     streven
    0.08
     minimizes
    0.08
     errors
    0.08
    Activations Density 0.018%

    No Known Activations