© 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. 63583
    Prev
    Next
    INDEX
    Explanations

    Religious rules and commandments

    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
    -0.08
     leveraging
    -0.07
     notable
    -0.07
     kert
    -0.07
     atop
    -0.07
     besser
    -0.07
    더
    -0.07
     better
    -0.07
    િત
    -0.07
    îte
    -0.07
    POSITIVE LOGITS
     abbreviation
    0.08
    _SY
    0.08
     অব
    0.08
     ceg
    0.08
     Nav
    0.08
     Blogging
    0.08
     Angels
    0.08
     blindness
    0.08
     STORE
    0.07
     Walsh
    0.07
    Activations Density 0.000%
    No Known Activations