© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 63091
    Prev
    Next
    INDEX
    Explanations

    scale

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UGIN
    -0.07
     гал
    -0.07
     spil
    -0.07
     excitation
    -0.07
    ward
    -0.07
    _DEFAULT
    -0.07
     supported
    -0.07
    either
    -0.07
    quence
    -0.07
    ，使
    -0.07
    POSITIVE LOGITS
    Meters
    0.09
     snapshot
    0.09
    -meter
    0.09
    (epoch
    0.09
     paycheck
    0.09
     meters
    0.09
     kilograms
    0.09
     kilos
    0.09
    (snapshot
    0.09
    斤
    0.09
    Activations Density 0.005%

    No Known Activations