© 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 EvalsExportsinterp-engineNEWAPI 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. 70791
    Prev
    Next
    INDEX
    Explanations

    line

    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
     ట్ర
    -0.10
    센터
    -0.08
     fortuna
    -0.08
     career
    -0.08
     chambers
    -0.08
    traf
    -0.08
     litigation
    -0.08
     ट्र
    -0.08
     bankrupt
    -0.08
     ears
    -0.07
    POSITIVE LOGITS
    -separated
    0.10
    Separated
    0.09
    (con
    0.08
    Indented
    0.08
    ർന്ന
    0.08
    _OCCURRED
    0.08
    Introdu
    0.08
     printer
    0.08
     introd
    0.08
     Comic
    0.08
    Activations Density 0.017%

    No Known Activations