© 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. 68325
    Prev
    Next
    INDEX
    Explanations

    pets

    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
     esfuerzos
    -0.09
     IDictionary
    -0.08
     poist
    -0.08
    Tho
    -0.08
     subsid
    -0.08
     pervasive
    -0.08
     reckon
    -0.07
     Handlung
    -0.07
     scattering
    -0.07
     manuscripts
    -0.07
    POSITIVE LOGITS
     hobby
    0.10
     housed
    0.10
     stored
    0.09
     nieces
    0.09
     Hobby
    0.09
     niece
    0.09
     arom
    0.08
     Stored
    0.08
     mascota
    0.08
     miniature
    0.08
    Activations Density 0.021%

    No Known Activations