© 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. 113250
    Prev
    Next
    INDEX
    Explanations

    chatbot dialogue

    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
     resultat
    -0.09
     sexuales
    -0.09
    ollo
    -0.08
    retto
    -0.08
    Med
    -0.08
     antwort
    -0.08
     dicembre
    -0.08
    irlpool
    -0.07
     सेक्स
    -0.07
     casar
    -0.07
    POSITIVE LOGITS
    简单
    0.08
    sz
    0.07
    actus
    0.07
     simple
    0.07
    ующих
    0.07
    етр
    0.07
    -based
    0.07
    াহত
    0.07
     Sab
    0.07
     eh
    0.07
    Activations Density 0.358%

    No Known Activations