© 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. 19-RESID-POST-AA
    11. 18568
    Prev
    Next
    INDEX
    Explanations

    variation

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    “There
    -0.08
    urized
    -0.08
     théorie
    -0.07
    Grâce
    -0.07
     dimens
    -0.07
    итан
    -0.07
     définition
    -0.07
    LEMENT
    -0.07
    elled
    -0.07
     существует
    -0.07
    POSITIVE LOGITS
     varying
    0.19
     vary
    0.19
     varies
    0.18
     varied
    0.18
     mostly
    0.17
     sometimes
    0.17
     varier
    0.16
     variados
    0.16
     variar
    0.16
     mix
    0.15
    Activations Density 0.004%

    No Known Activations