© 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. 3-RESID-POST-AA
    11. 908
    Prev
    Next
    INDEX
    Explanations

    Code and mixed text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     erupted
    -0.08
    િર
    -0.08
     Hate
    -0.08
     cuál
    -0.08
     sput
    -0.08
     quale
    -0.07
     начиная
    -0.07
     esperamos
    -0.07
    ینو
    -0.07
     unem
    -0.07
    POSITIVE LOGITS
    sms
    0.08
    gen
    0.07
    144
    0.07
    har
    0.07
     muscle
    0.07
     ken
    0.07
     proficiency
    0.07
    添
    0.07
    weisen
    0.07
     vegetal
    0.07
    Activations Density 0.000%

    No Known Activations