© 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. 5698
    Prev
    Next
    INDEX
    Explanations

    Foreign language, codes, symbols

    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
    icial
    -0.08
     vinc
    -0.08
     ogen
    -0.08
    udya
    -0.08
    ishment
    -0.07
     lengkap
    -0.07
    legen
    -0.07
     exclusivos
    -0.07
     apan
    -0.07
    iciar
    -0.07
    POSITIVE LOGITS
    iper
    0.10
    ipers
    0.09
    iority
    0.09
    տեմբերի
    0.08
     Matches
    0.08
    ί
    0.08
    ipad
    0.08
    cto
    0.08
    eron
    0.08
     ম্যাচ
    0.08
    Activations Density 0.001%

    No Known Activations