© 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. 99567
    Prev
    Next
    INDEX
    Explanations

    fore

    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
    	lua
    -0.08
    	ans
    -0.08
    	reply
    -0.08
    ুয
    -0.08
    요일
    -0.08
     uv
    -0.08
     atu
    -0.08
     lanjut
    -0.08
     ans
    -0.08
    duce
    -0.08
    POSITIVE LOGITS
     foreclosure
    0.14
     bankrupt
    0.10
     hipotec
    0.10
     ипот
    0.10
     bankruptcy
    0.09
     mortgages
    0.09
     mortgage
    0.08
    Winner
    0.08
     कब्ज
    0.08
     auction
    0.08
    Activations Density 0.020%

    No Known Activations