© 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. 44644
    Prev
    Next
    INDEX
    Explanations

    irrational numbers, decimals

    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
     מת
    -0.09
     मूल
    -0.08
     साह
    -0.07
     метод
    -0.07
     см
    -0.07
     leichter
    -0.07
     erbij
    -0.07
     프로젝트
    -0.07
     enlisted
    -0.07
     появ
    -0.07
    POSITIVE LOGITS
    clam
    0.09
    .mine
    0.07
    _duplicates
    0.07
     Numerous
    0.07
    _I
    0.07
    atorias
    0.07
     ores
    0.07
     Rece
    0.07
    煤
    0.07
     Ogun
    0.07
    Activations Density 0.017%

    No Known Activations