© 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. 23-RESID-POST-AA
    6. 5520
    Prev
    Next
    INDEX
    Explanations

    final

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wherein
    -0.10
     analyzed
    -0.10
     experimented
    -0.10
     causes
    -0.10
    	WHERE
    -0.10
    骗人的
    -0.10
     cuyos
    -0.09
     potentially
    -0.09
    ختلف
    -0.09
    														
    -0.09
    POSITIVE LOGITS
     is
    0.19
     answer
    0.17
     are
    0.16
     adalah
    0.16
     것은
    0.15
     would
    0.14
    は
    0.14
    的是
    0.14
    是
    0.13
    ly
    0.13
    Activations Density 0.113%

    No Known Activations