© 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. 3-RESID-POST-AA
    11. 13245
    Prev
    Next
    INDEX
    Explanations

    Exchange

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ant
    -0.07
    fox
    -0.07
    طة
    -0.07
    -0.07
     wajah
    -0.07
    letter
    -0.07
    보
    -0.07
    uenza
    -0.07
     incó
    -0.07
     cheeks
    -0.07
    POSITIVE LOGITS
     qualit
    0.07
     Curt
    0.07
    636
    0.07
    	scale
    0.07
    	pos
    0.07
     filters
    0.07
    	wp
    0.07
    共同
    0.07
     Nichols
    0.07
     Basin
    0.07
    Activations Density 0.000%
    No Known Activations