© 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. 24926
    Prev
    Next
    INDEX
    Explanations

    physics, plasma, colliders

    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
     拉
    -0.08
     }.
    -0.07
    eslint
    -0.07
     afh
    -0.07
     yaiku
    -0.07
     policiais
    -0.07
    PRI
    -0.07
    .authentication
    -0.07
     fuq
    -0.07
     قرارد
    -0.07
    POSITIVE LOGITS
    Mesa
    0.10
     Mesa
    0.09
    ulations
    0.08
     rave
    0.08
    às
    0.08
    "value
    0.08
     Madness
    0.08
    'ọ
    0.08
     chaos
    0.08
     Indie
    0.08
    Activations Density 0.001%

    No Known Activations