© 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. 19604
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ==
    -0.07
    ==
    -0.07
    politik
    -0.07
    =false
    -0.07
    Ori
    -0.07
    _selection
    -0.07
    jni
    -0.07
    jali
    -0.07
    .Al
    -0.07
    ophobia
    -0.07
    POSITIVE LOGITS
     multiplied
    0.12
    züglich
    0.11
     ..."
    0.11
     сумма
    0.10
     сумму
    0.10
     multiples
    0.10
     գում
    0.10
    乘
    0.10
     gallons
    0.10
     ჩემი
    0.10
    Activations Density 0.015%

    No Known Activations