© 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. 22302
    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
    DOG
    -0.08
    _SMS
    -0.08
    pers
    -0.08
     Survey
    -0.08
    .pdf
    -0.08
     unemployed
    -0.08
    _timeout
    -0.08
     TELE
    -0.07
     telefonisch
    -0.07
    /contact
    -0.07
    POSITIVE LOGITS
     nourish
    0.21
     nourishing
    0.21
     nourishment
    0.17
     nutritious
    0.17
     wholesome
    0.17
     voed
    0.17
     delicious
    0.16
     tasty
    0.15
     flavorful
    0.15
     अच्छ
    0.14
    Activations Density 0.026%

    No Known Activations