© 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. 19-RESID-POST-AA
    11. 103359
    Prev
    Next
    INDEX
    Explanations

    coefficients

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ική
    -0.08
    ẹp
    -0.08
     możliwości
    -0.08
     padrão
    -0.08
    -transform
    -0.08
    ，让
    -0.08
    ικές
    -0.08
     Möglichkeiten
    -0.07
     welzijn
    -0.07
     Transformer
    -0.07
    POSITIVE LOGITS
     ]),↵
    0.08
    ]),↵
    0.08
    .,↵
    0.08
    /etc
    0.08
    ']),↵
    0.08
     )),↵
    0.07
    롯
    0.07
    /km
    0.07
    ],↵
    0.07
    0.07
    Activations Density 0.000%

    No Known Activations