© 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. 110299
    Prev
    Next
    INDEX
    Explanations

    /24 network sizes

    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
    _V
    -0.08
     computadora
    -0.08
     undec
    -0.07
    γράφ
    -0.07
     brutal
    -0.07
    .chomp
    -0.07
    jan
    -0.07
     intellectually
    -0.07
    年
    -0.07
    Vertex
    -0.07
    POSITIVE LOGITS
     cis
    0.08
    ohner
    0.08
    ","\
    0.07
     Man
    0.07
     φ
    0.07
    ucos
    0.07
     uc
    0.07
     అంటే
    0.07
     ending
    0.07
     circuit
    0.07
    Activations Density 0.001%

    No Known Activations