© 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. 69268
    Prev
    Next
    INDEX
    Explanations

    history/geography texts

    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
     filed
    -0.09
    юсь
    -0.08
     конф
    -0.08
     juridique
    -0.08
     ಕಾರ್ಯ
    -0.08
     consequent
    -0.07
     clichés
    -0.07
     bancaire
    -0.07
     warranty
    -0.07
     qualification
    -0.07
    POSITIVE LOGITS
     mound
    0.10
    _NATIVE
    0.10
     tribes
    0.09
     indigenous
    0.09
     مكة
    0.09
     ulu
    0.09
     colonial
    0.09
     tribe
    0.09
     clans
    0.09
     maize
    0.09
    Activations Density 0.028%

    No Known Activations