© 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. 110359
    Prev
    Next
    INDEX
    Explanations

    circle

    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
     spiritual
    -0.09
     wächst
    -0.08
     vrai
    -0.08
     accountants
    -0.07
     спир
    -0.07
     logist
    -0.07
    औ
    -0.07
     størrelse
    -0.07
     cushion
    -0.07
     Accountant
    -0.07
    POSITIVE LOGITS
     реч
    0.07
    娱
    0.07
     circuit
    0.07
     subgroup
    0.07
    ikip
    0.07
    862
    0.07
    ーデ
    0.07
    isable
    0.07
    romatic
    0.07
     desblo
    0.07
    Activations Density 0.002%

    No Known Activations