© 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. 11-RESID-POST-AA
    11. 71232
    Prev
    Next
    INDEX
    Explanations

    classical conditioning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     içine
    -0.08
    feiço
    -0.08
     junio
    -0.08
     supuesto
    -0.08
    aport
    -0.07
    nu
    -0.07
     Neighborhood
    -0.07
    .Export
    -0.07
    along
    -0.07
     rid
    -0.07
    POSITIVE LOGITS
     triggering
    0.16
     triggers
    0.15
    	trigger
    0.13
     trigger
    0.13
    Trigger
    0.12
    (trigger
    0.12
    Triggers
    0.12
    .trigger
    0.12
    -trigger
    0.11
    trigger
    0.11
    Activations Density 0.029%

    No Known Activations