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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 99306
    Prev
    Next
    INDEX
    Explanations

    ref

    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
    Dj
    -0.09
    _INTERVAL
    -0.08
    /h
    -0.08
    elings
    -0.08
    	target
    -0.08
    /ng
    -0.07
     jelly
    -0.07
    	org
    -0.07
     wez
    -0.07
     آه
    -0.07
    POSITIVE LOGITS
     geschaffen
    0.08
    ampton
    0.08
    刊
    0.07
    mouseenter
    0.07
     paginate
    0.07
     Bande
    0.07
     Usted
    0.07
     Gender
    0.07
     공유
    0.07
     Breakfast
    0.07
    Activations Density 0.000%

    No Known Activations