© 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. 44682
    Prev
    Next
    INDEX
    Explanations

    Math arrays

    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
     Helpers
    -0.08
     auxiliar
    -0.08
     Arab
    -0.08
     comparer
    -0.07
    'article
    -0.07
    article
    -0.07
     Helper
    -0.07
    @end
    -0.07
     artículo
    -0.07
     sigue
    -0.07
    POSITIVE LOGITS
    jel
    0.08
    >N
    0.08
     stead
    0.07
     altru
    0.07
    ’am
    0.07
    >M
    0.07
    >[]
    0.07
    ichael
    0.07
    ดำ
    0.07
     slots
    0.07
    Activations Density 0.000%

    No Known Activations