© 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. 70965
    Prev
    Next
    INDEX
    Explanations

    maple

    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
    局
    -0.08
    ceis
    -0.08
    kele
    -0.08
    �
    -0.08
     embarked
    -0.08
     polar
    -0.08
    can
    -0.07
    .RESULT
    -0.07
     studied
    -0.07
    ice
    -0.07
    POSITIVE LOGITS
     noop
    0.09
     rgba
    0.09
    /npm
    0.09
    -exclusive
    0.08
    Provision
    0.08
     exclusivement
    0.08
    .Composite
    0.08
     berasal
    0.08
     Toujours
    0.08
     uttry
    0.08
    Activations Density 0.001%

    No Known Activations