© 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. 18681
    Prev
    Next
    INDEX
    Explanations

    say "_y or 2"

    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
     voire
    -0.08
     heart
    -0.07
     náv
    -0.07
     控
    -0.07
     både
    -0.07
     tanto
    -0.07
     ää
    -0.07
     Controle
    -0.07
     外
    -0.07
     zowel
    -0.07
    POSITIVE LOGITS
    _x
    0.12
    _y
    0.11
    _z
    0.11
    _small
    0.11
    .y
    0.10
    .z
    0.10
    _X
    0.10
    барат
    0.09
    rrüň
    0.09
    _在线
    0.09
    Activations Density 0.002%

    No Known Activations