© 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. 26128
    Prev
    Next
    INDEX
    Explanations

    diagrams and code

    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
    _AMOUNT
    -0.09
    +.
    -0.09
     الأكثر
    -0.08
     bills
    -0.08
     Bill
    -0.08
     expl
    -0.08
     Bills
    -0.07
     अशी
    -0.07
     willingly
    -0.07
    الب
    -0.07
    POSITIVE LOGITS
    Bridge
    0.08
    Photon
    0.08
    Hor
    0.08
    .finance
    0.08
    Proxy
    0.08
    serializer
    0.07
     Brides
    0.07
    社会主义
    0.07
     aloe
    0.07
     Bridge
    0.07
    Activations Density 0.009%

    No Known Activations