© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 95475
    Prev
    Next
    INDEX
    Explanations

    nested cluster

    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
     philanthrop
    -0.09
     philanthropic
    -0.08
     Mediterranean
    -0.07
     Dante
    -0.07
     wardrobe
    -0.07
     Byzant
    -0.07
     union
    -0.07
     Вост
    -0.07
     decom
    -0.07
    mez
    -0.07
    POSITIVE LOGITS
     clustering
    0.09
     cluster
    0.09
    Cluster
    0.09
    cluster
    0.09
     Cluster
    0.09
    	cluster
    0.08
    Treatment
    0.08
    .cluster
    0.08
    _cluster
    0.08
     datasource
    0.08
    Activations Density 0.003%

    No Known Activations