© 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. 23-RESID-POST-AA
    11. 51527
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     производится
    -0.09
     lavor
    -0.09
     произвед
    -0.08
     trabajar
    -0.08
     workstation
    -0.08
     производ
    -0.08
     работ
    -0.08
     trabalhar
    -0.08
     tinnitus
    -0.08
     presencial
    -0.08
    POSITIVE LOGITS
    pox
    0.09
    Et
    0.09
    拉
    0.08
     sled
    0.08
    _th
    0.08
     拉
    0.08
    _et
    0.08
    _s
    0.08
    _pull
    0.08
    igno
    0.08
    Activations Density 0.001%

    No Known Activations