© 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. 23-RESID-POST-AA
    11. 49145
    Prev
    Next
    INDEX
    Explanations

    say "E" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jasa
    -0.09
     palvel
    -0.08
    마사지
    -0.08
    rops
    -0.08
     gasoline
    -0.08
     hizmet
    -0.08
     polite
    -0.08
     parasito
    -0.08
     asesor
    -0.08
    Taxi
    -0.08
    POSITIVE LOGITS
     Electronic
    0.23
     electronic
    0.21
     elektronische
    0.21
    Electronic
    0.20
     इलेक्ट्र
    0.19
     elektron
    0.19
     EM
    0.19
    電子
    0.18
    电子
    0.18
     электрон
    0.18
    Activations Density 0.043%

    No Known Activations