© 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 EvalsExportsAPI 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. 49940
    Prev
    Next
    INDEX
    Explanations

    w

    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
    ROME
    -0.08
     Managing
    -0.08
    Lor
    -0.08
    posite
    -0.07
     Convention
    -0.07
     mimo
    -0.07
    rome
    -0.07
    vue
    -0.07
    .meg
    -0.07
     dispositifs
    -0.07
    POSITIVE LOGITS
    aver
    0.16
    avers
    0.13
    ane
    0.13
    avering
    0.12
    obb
    0.12
    anes
    0.11
     averaged
    0.11
     averaging
    0.09
    aning
    0.09
    ither
    0.08
    Activations Density 0.001%

    No Known Activations