© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 65410
    Prev
    Next
    INDEX
    Explanations

    this

    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
     EG
    -0.09
     Shan
    -0.08
    甲
    -0.08
     ENG
    -0.07
    �
    -0.07
     бор
    -0.07
     découvre
    -0.07
     AF
    -0.07
     sooner
    -0.07
     ENV
    -0.07
    POSITIVE LOGITS
    plus
    0.08
     izra
    0.08
     aver
    0.08
     obil
    0.08
     heroin
    0.08
    /by
    0.07
     Sauv
    0.07
     சொ
    0.07
     Сем
    0.07
    -là
    0.07
    Activations Density 0.043%

    No Known Activations