© 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. 110827
    Prev
    Next
    INDEX
    Explanations

    medieval fantasy

    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
     leuke
    -0.10
     അമേരിക്ക
    -0.09
     américaine
    -0.09
     sympathique
    -0.09
    American
    -0.09
     American
    -0.09
    urrent
    -0.09
    炒
    -0.08
    Servlet
    -0.08
    urdue
    -0.08
    POSITIVE LOGITS
     ancient
    0.14
     древ
    0.13
     Ancient
    0.12
     battlefield
    0.12
     vengeance
    0.12
     divine
    0.11
     forged
    0.11
     warriors
    0.11
     warrior
    0.11
     quests
    0.11
    Activations Density 0.199%

    No Known Activations