© 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. 79338
    Prev
    Next
    INDEX
    Explanations

    finance and legal context

    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
    .append
    -0.09
    append
    -0.08
     append
    -0.07
    عادة
    -0.07
    îte
    -0.07
    �
    -0.07
    fügbarkeit
    -0.07
     η
    -0.07
    ニ
    -0.07
    <|endoftext|>
    -0.07
    POSITIVE LOGITS
     pensado
    0.08
    akr
    0.08
     pencils
    0.08
     Jerusal
    0.08
     Vortrag
    0.08
     Knot
    0.08
     concepto
    0.08
     syllabus
    0.08
     meinst
    0.08
     Hector
    0.08
    Activations Density 0.000%

    No Known Activations