© 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. 51020
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
     niente
    -0.10
    นัน
    -0.10
    ónaí
    -0.09
     bæ
    -0.09
    ేది
    -0.09
    анбе
    -0.09
     soporte
    -0.09
    дени
    -0.09
    奶头
    -0.09
    ʻani
    -0.09
    POSITIVE LOGITS
    250
    0.13
    260
    0.13
    255
    0.12
    88
    0.12
    265
    0.12
    259
    0.12
    25
    0.12
    89
    0.11
    257
    0.11
    256
    0.11
    Activations Density 0.107%

    No Known Activations