© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 102137
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     simpler
    -0.10
     és
    -0.09
    nine
    -0.09
     illetve
    -0.09
    人与
    -0.09
     drejt
    -0.09
    posite
    -0.09
    	foreach
    -0.09
    ότε
    -0.08
     और
    -0.08
    POSITIVE LOGITS
     können
    0.09
     can
    0.08
     possono
    0.08
     dapat
    0.08
     peuvent
    0.08
     mohou
    0.08
     يمكن
    0.07
     LA
    0.07
     maaari
    0.07
     LM
    0.07
    Activations Density 0.000%

    No Known Activations