© 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. 233
    Prev
    Next
    INDEX
    Explanations

    multilingual text; answering prompts

    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
    (and
    -0.09
     Numerous
    -0.09
    .should
    -0.08
     Schwe
    -0.08
    <object
    -0.08
    -enabled
    -0.08
    NEY
    -0.08
    -supported
    -0.08
    Ns
    -0.08
    SY
    -0.08
    POSITIVE LOGITS
    意义
    0.10
     notion
    0.09
    传统
    0.09
     معنى
    0.09
    meaning
    0.09
     traditional
    0.09
    意味
    0.09
     concept
    0.08
     notions
    0.08
     nghĩa
    0.08
    Activations Density 0.013%

    No Known Activations