© 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. 23-RESID-POST-AA
    11. 49483
    Prev
    Next
    INDEX
    Explanations

    robots

    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
     graduação
    -0.08
    (er
    -0.08
    (enum
    -0.08
     پاڻي
    -0.08
    erweise
    -0.07
    agraph
    -0.07
    ત
    -0.07
     aguas
    -0.07
     phases
    -0.07
    alach
    -0.07
    POSITIVE LOGITS
    �
    0.14
    机器人
    0.14
    BOT
    0.13
    Roboto
    0.12
     Transformers
    0.12
     bots
    0.12
    Cyber
    0.12
    .bot
    0.12
    Bot
    0.12
    bot
    0.12
    Activations Density 0.019%

    No Known Activations