© 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. 24673
    Prev
    Next
    INDEX
    Explanations

    Code and programming languages

    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
    memor
    -0.09
     Memor
    -0.09
     Prius
    -0.08
     viktigt
    -0.08
    gata
    -0.08
     강조
    -0.08
     prayed
    -0.08
    dresser
    -0.08
    ्प
    -0.08
     belangrijk
    -0.08
    POSITIVE LOGITS
     кітап
    0.11
    库
    0.11
     library
    0.10
     библиот
    0.10
     βιβ
    0.10
     knih
    0.09
     நூ
    0.09
     библи
    0.09
     libraries
    0.09
     lib
    0.09
    Activations Density 0.032%

    No Known Activations