© 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. 18333
    Prev
    Next
    INDEX
    Explanations

    increments

    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
    ynthesize
    -0.08
    insi
    -0.07
     hiç
    -0.07
     çocuk
    -0.07
    昔
    -0.07
     Emin
    -0.07
     wyb
    -0.07
    ütfen
    -0.07
     nasıl
    -0.07
     hogyan
    -0.07
    POSITIVE LOGITS
     +=
    0.15
    .increment
    0.15
     contributes
    0.13
    increment
    0.13
    增加
    0.13
    _increment
    0.12
    ++;
    0.12
     aumenta
    0.12
    ++;↵↵
    0.12
     daquele
    0.12
    Activations Density 0.035%

    No Known Activations