© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 31522
    Prev
    Next
    INDEX
    Explanations

    such

    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
     Institutional
    -0.08
     senador
    -0.08
     insurers
    -0.08
    unes
    -0.08
     sidan
    -0.08
    க்கம்
    -0.07
     NPR
    -0.07
    اتهم
    -0.07
    aned
    -0.07
    arlar
    -0.07
    POSITIVE LOGITS
     �
    0.07
     kindly
    0.07
     intervention
    0.07
     Gior
    0.07
     Kis
    0.07
     Mediterranean
    0.07
     μέ
    0.07
     who
    0.07
     :
    0.07
     century
    0.07
    Activations Density 0.000%

    No Known Activations