© 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. 24851
    Prev
    Next
    INDEX
    Explanations

    maximizing product given sum

    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
     Kens
    -0.08
     Rush
    -0.07
    (rc
    -0.07
    ,function
    -0.07
    ('//
    -0.07
    (tc
    -0.07
     Vec
    -0.07
     jedn
    -0.07
     જોઈ
    -0.07
     Heer
    -0.07
    POSITIVE LOGITS
    ’z
    0.08
     খাদ
    0.08
    -media
    0.07
    .media
    0.07
     আত
    0.07
    잘
    0.07
     revive
    0.07
    -rating
    0.07
     financier
    0.07
    37
    0.07
    Activations Density 0.008%

    No Known Activations