© 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 EvalsExportsAPI 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. 64246
    Prev
    Next
    INDEX
    Explanations

    cloud managed services

    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
    ático
    -0.08
    क्सर
    -0.07
     clockwise
    -0.07
    -0.07
     
    -0.07
     wearer
    -0.07
    _warn
    -0.07
     heel
    -0.07
    老板
    -0.07
     consenso
    -0.07
    POSITIVE LOGITS
     Dynamo
    0.09
    .amazonaws
    0.09
     parallels
    0.09
     AWS
    0.08
    AWS
    0.08
    Azure
    0.08
    ’offre
    0.08
    治理
    0.08
     Azure
    0.08
    _firestore
    0.08
    Activations Density 0.013%
    No Known Activations