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. 78653
    Prev
    Next
    INDEX
    Explanations

    benefits

    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
    rë
    -0.08
     memorable
    -0.08
     전체
    -0.08
     kreative
    -0.08
    _inode
    -0.08
     브랜드
    -0.08
    isessä
    -0.08
     arbitrary
    -0.08
     Kil
    -0.07
     bütün
    -0.07
    POSITIVE LOGITS
    领取
    0.13
     pensions
    0.10
    申
    0.10
     Leistungen
    0.10
     pension
    0.10
     Medicaid
    0.09
    申请
    0.09
     Medicare
    0.09
     신청
    0.09
     medications
    0.09
    Activations Density 0.025%

    No Known Activations