© 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 EvalsExportsAPI 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. 113613
    Prev
    Next
    INDEX
    Explanations

    Writing to a file

    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
    getting
    -0.08
     LP
    -0.08
     tric
    -0.08
    77
    -0.08
    .ship
    -0.08
     pensando
    -0.08
     néanmoins
    -0.08
    VEL
    -0.08
    uluş
    -0.08
    শ
    -0.07
    POSITIVE LOGITS
     Bax
    0.08
     osvoj
    0.07
     jednoduch
    0.07
     spoj
    0.07
     slov
    0.07
    ائے
    0.07
     muro
    0.07
     оң
    0.07
     sencillo
    0.07
     buon
    0.07
    Activations Density 0.000%

    No Known Activations