© 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. 5578
    Prev
    Next
    INDEX
    Explanations

    def

    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
     Aroma
    -0.07
    ects
    -0.07
     jardin
    -0.07
    jä
    -0.07
    525
    -0.07
    ik
    -0.07
     unified
    -0.07
     primarily
    -0.07
    ’я
    -0.07
    OMO
    -0.07
    POSITIVE LOGITS
    erral
    0.19
    errals
    0.19
    erring
    0.17
    ERR
    0.13
    err
    0.12
     defer
    0.12
    Deferred
    0.12
     deferred
    0.11
    ferred
    0.11
    延期
    0.11
    Activations Density 0.001%

    No Known Activations