© 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. 3120
    Prev
    Next
    INDEX
    Explanations

    txt

    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
     scrum
    -0.08
     α
    -0.08
     Scrum
    -0.08
     état
    -0.08
     Madh
    -0.08
    	type
    -0.08
     headset
    -0.07
     speed
    -0.07
    िल्ल
    -0.07
     হার
    -0.07
    POSITIVE LOGITS
     schwarzen
    0.09
     spur
    0.08
     boldly
    0.08
     negro
    0.08
     schwarze
    0.08
    IMENTO
    0.08
    asto
    0.07
    먼
    0.07
    beren
    0.07
    Integration
    0.07
    Activations Density 0.000%

    No Known Activations