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. 130383
    Prev
    Next
    INDEX
    Explanations

    Standards

    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
     abgeschlossen
    -0.08
     beslut
    -0.08
     alias
    -0.08
    lä
    -0.08
     মাধ্যম
    -0.08
    사진
    -0.08
    决
    -0.08
     AUT
    -0.08
    qar
    -0.07
     aes
    -0.07
    POSITIVE LOGITS
     wages
    0.12
     wage
    0.12
     노동
    0.12
     Wage
    0.11
     statutory
    0.11
    福利
    0.10
     मजद
    0.10
     trabalhador
    0.10
     laborales
    0.10
    工资
    0.10
    Activations Density 0.017%

    No Known Activations