© 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. 21959
    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
     cliente
    -0.09
    _CLIENT
    -0.08
    ünscht
    -0.08
    hados
    -0.08
     adaptación
    -0.08
     клі
    -0.08
     клиента
    -0.08
     mínimos
    -0.08
    _CANCEL
    -0.08
    keletal
    -0.08
    POSITIVE LOGITS
    ENG
    0.08
     Winston
    0.08
     Earl
    0.08
    behavior
    0.08
    :variables
    0.07
    :set
    0.07
    auro
    0.07
     angels
    0.07
     Functions
    0.07
    ាតិ
    0.07
    Activations Density 0.045%

    No Known Activations