© 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. 45453
    Prev
    Next
    INDEX
    Explanations

    Timeout

    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
     maman
    -0.07
     छात्र
    -0.07
    יי
    -0.07
     protest
    -0.07
     unem
    -0.07
     अपन
    -0.07
     youth
    -0.07
     தேதி
    -0.07
     üh
    -0.07
    akes
    -0.07
    POSITIVE LOGITS
    707
    0.08
    યોગ
    0.07
    720
    0.07
     dæ
    0.07
    linen
    0.07
     �
    0.07
     teaser
    0.07
     roku
    0.07
     centrif
    0.07
    701
    0.07
    Activations Density 0.001%

    No Known Activations