© 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. 112664
    Prev
    Next
    INDEX
    Explanations

    triangle

    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
     ijs
    -0.08
     co
    -0.08
     النس
    -0.08
     Checkbox
    -0.08
     romance
    -0.07
    خان
    -0.07
     المال
    -0.07
     intimacy
    -0.07
     rocky
    -0.07
     hype
    -0.07
    POSITIVE LOGITS
     loudly
    0.11
     चम
    0.10
     louder
    0.09
     તે�
    0.09
    Visibility
    0.08
     наруж
    0.08
     Visibility
    0.08
     unmistak
    0.08
     चिन
    0.08
    đer
    0.08
    Activations Density 0.011%

    No Known Activations