© 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. 71332
    Prev
    Next
    INDEX
    Explanations

    operation

    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
    etzen
    -0.09
     Module
    -0.08
    icha
    -0.08
    etze
    -0.08
     desped
    -0.07
    undo
    -0.07
    apped
    -0.07
    .mutable
    -0.07
    .forward
    -0.07
    fra
    -0.07
    POSITIVE LOGITS
     informa
    0.08
     hi
    0.08
     informació
    0.08
     দৈ
    0.07
     wont
    0.07
     accesses
    0.07
     prad
    0.07
     economie
    0.07
     Sw
    0.07
     دین
    0.07
    Activations Density 0.683%

    No Known Activations