© 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. 63489
    Prev
    Next
    INDEX
    Explanations

    people

    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
     geom
    -0.08
     Erinnerung
    -0.07
     remembrance
    -0.07
    (__
    -0.07
     rappelle
    -0.07
     memory
    -0.07
    acf
    -0.07
    Memory
    -0.07
     locking
    -0.07
     om
    -0.07
    POSITIVE LOGITS
     outreach
    0.10
     Outreach
    0.09
     atraer
    0.09
    Converted
    0.09
     Converted
    0.09
     überzeug
    0.09
     attracted
    0.09
     casual
    0.09
     Casual
    0.08
     demographics
    0.08
    Activations Density 0.046%

    No Known Activations