© 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. 70986
    Prev
    Next
    INDEX
    Explanations

    projector specifications

    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
    /export
    -0.08
    /all
    -0.07
    делі
    -0.07
     encouragement
    -0.07
    емен
    -0.07
    AYA
    -0.07
    alara
    -0.07
     indifferent
    -0.07
     linkage
    -0.07
     aluminum
    -0.07
    POSITIVE LOGITS
    倍
    0.08
     matat
    0.08
     よ
    0.08
    起来
    0.08
    容易
    0.08
     쉽게
    0.08
     ఎంద
    0.07
     എഴ
    0.07
     کان
    0.07
    pli
    0.07
    Activations Density 0.000%

    No Known Activations