© 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. 95036
    Prev
    Next
    INDEX
    Explanations

    attract

    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
     CONTROL
    -0.08
     Vorg
    -0.08
     orale
    -0.08
     قسمت
    -0.07
     Teller
    -0.07
     Aux
    -0.07
    APA
    -0.07
     stressed
    -0.07
     kana
    -0.07
     Oficina
    -0.07
    POSITIVE LOGITS
     talent
    0.10
    资金
    0.09
     внимание
    0.09
     લોકોને
    0.09
    人才
    0.09
     निध
    0.09
     attention
    0.09
     внимания
    0.09
     uwagę
    0.09
     talento
    0.09
    Activations Density 0.039%

    No Known Activations