© 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. 96634
    Prev
    Next
    INDEX
    Explanations

    Chants and cheers

    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
     newsroom
    -0.08
     Disclosure
    -0.07
     rijk
    -0.07
    @Target
    -0.07
     errands
    -0.07
     Equ
    -0.07
    .Assertions
    -0.07
     Careers
    -0.07
     quaint
    -0.07
     Workplace
    -0.07
    POSITIVE LOGITS
     chants
    0.19
     chanting
    0.17
     cheers
    0.16
     ова
    0.16
     Cheers
    0.15
     chant
    0.15
     roar
    0.15
    Cheers
    0.14
     जय
    0.14
     boos
    0.14
    Activations Density 0.039%

    No Known Activations