© 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. 114133
    Prev
    Next
    INDEX
    Explanations

    inn

    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
    .Cascade
    -0.09
     incentivar
    -0.09
     Fert
    -0.08
    落
    -0.08
    Fmt
    -0.08
    (UInt
    -0.08
     dager
    -0.08
     prototype
    -0.07
     Justiça
    -0.07
     ness
    -0.07
    POSITIVE LOGITS
     backward
    0.07
     washers
    0.07
     미
    0.07
    components
    0.07
     х
    0.07
     ним
    0.07
    listeners
    0.07
     ray
    0.07
    +\
    0.07
     midfield
    0.07
    Activations Density 0.001%

    No Known Activations