© 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. 21465
    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
    _need
    -0.11
    必须
    -0.11
     실제
    -0.11
    utuhkan
    -0.10
     Actual
    -0.10
     tatsäch
    -0.10
     fordi
    -0.10
     brauchst
    -0.10
     Actually
    -0.10
     патрэ
    -0.10
    POSITIVE LOGITS
     préciser
    0.17
     specifying
    0.17
     specify
    0.16
     specifies
    0.16
     especific
    0.15
     уточ
    0.15
     specified
    0.15
     निर्द
    0.14
    指定
    0.14
     qualifiers
    0.14
    Activations Density 0.019%

    No Known Activations