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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 43138
    Prev
    Next
    INDEX
    Explanations

    achievement

    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
    사업
    -0.08
    .trip
    -0.08
     Hotel
    -0.07
    .scheduler
    -0.07
     dùng
    -0.07
     проду
    -0.07
     Prote
    -0.07
     Reservation
    -0.07
    рама
    -0.07
     kino
    -0.07
    POSITIVE LOGITS
    成绩
    0.14
     IELTS
    0.12
     literacy
    0.11
     aptitude
    0.10
     attainment
    0.10
     academically
    0.10
     grades
    0.10
     proficiency
    0.10
     tutoring
    0.09
     олим
    0.09
    Activations Density 0.018%

    No Known Activations