© 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. 110767
    Prev
    Next
    INDEX
    Explanations

    Alternate

    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
    (debug
    -0.08
     inci
    -0.08
     направ
    -0.07
    (poly
    -0.07
    (days
    -0.07
    Ip
    -0.07
     combined
    -0.07
    Ary
    -0.07
     الفرد
    -0.07
     carefully
    -0.07
    POSITIVE LOGITS
     counterparts
    0.09
     counterpart
    0.08
     lain
    0.07
     മുഖ
    0.07
    _lon
    0.07
    steen
    0.07
     സംഘ
    0.07
     Meh
    0.07
     sand
    0.07
    worthiness
    0.07
    Activations Density 0.003%

    No Known Activations