© 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. 47872
    Prev
    Next
    INDEX
    Explanations

    Build systems and tools

    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
    classifier
    -0.09
     статье
    -0.09
     publishes
    -0.09
    лица
    -0.08
    发布日期
    -0.08
     produzir
    -0.08
     дерева
    -0.08
    BIN
    -0.08
    镜
    -0.08
     producing
    -0.08
    POSITIVE LOGITS
     Ant
    0.12
     Aut
    0.12
    Ant
    0.11
     ant
    0.10
    Aut
    0.10
    .ant
    0.09
    _ant
    0.09
    .Aut
    0.09
    'aut
    0.09
     Ninja
    0.09
    Activations Density 0.002%

    No Known Activations