© 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. 21537
    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
    airobi
    -0.09
     Blackjack
    -0.08
     Vip
    -0.08
     Nationale
    -0.08
     Estonia
    -0.08
     Mahjong
    -0.08
    演
    -0.08
    apala
    -0.08
     gug
    -0.08
     blackjack
    -0.08
    POSITIVE LOGITS
     cyst
    0.18
     CF
    0.16
    CF
    0.14
     mucus
    0.13
    _CF
    0.13
     bronch
    0.12
     COPD
    0.11
    _cf
    0.11
     airway
    0.11
     chloride
    0.11
    Activations Density 0.002%

    No Known Activations