© 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. 7-RESID-POST-AA
    11. 1139
    Prev
    Next
    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    职责
    -0.09
    推进
    -0.09
    负责
    -0.09
     ходе
    -0.08
    Qo
    -0.08
     handic
    -0.08
     बाकी
    -0.08
     illet
    -0.08
    各种
    -0.08
    ipat
    -0.07
    POSITIVE LOGITS
     optar
    0.09
     opção
    0.08
     circum
    0.08
     tolerated
    0.08
     opción
    0.08
     hacerlo
    0.08
     eignet
    0.08
     suerte
    0.08
     sobres
    0.08
     lasers
    0.08
    Activations Density 0.025%

    No Known Activations