© 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. 7822
    Prev
    Next
    INDEX
    Explanations

    rules or settings

    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
    东西
    -0.08
     Ane
    -0.08
     vooral
    -0.08
     nada
    -0.08
     sería
    -0.07
    Something
    -0.07
     Elizabeth
    -0.07
     nenhuma
    -0.07
    ira
    -0.07
     Hoewel
    -0.07
    POSITIVE LOGITS
    -defined
    0.11
     predetermined
    0.11
     previamente
    0.10
     predefined
    0.10
     Defined
    0.09
     chosen
    0.09
    ာ
    0.09
    defined
    0.09
     установлен
    0.09
    规定
    0.09
    Activations Density 0.115%

    No Known Activations