Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 471
    Prev
    Next
    INDEX
    Explanations

    notes

    np_max-act · gemini-2.0-flash

    instructions and setup guidance.

    oai_token-act-pair · gpt-5-nanoTriggered by @tatsatx
    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
     kör
    -0.08
     আব
    -0.08
    <Document
    -0.08
     ebb
    -0.08
    حاد
    -0.08
    _literals
    -0.07
     Wohnzimmer
    -0.07
    arty
    -0.07
     legít
    -0.07
     certamente
    -0.07
    POSITIVE LOGITS
    사항
    0.10
    事项
    0.09
     note
    0.09
     NOTE
    0.09
    事項
    0.09
     beachten
    0.09
     rekl
    0.08
     toutefois
    0.08
     IMPORTANT
    0.08
     사항
    0.08
    Activations Density 0.035%

    No Known Activations