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. 55008
    Prev
    Next
    INDEX
    Explanations

    Math word problems

    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
     cleavage
    -0.09
     hist
    -0.08
     satisfying
    -0.07
     domain
    -0.07
     저장
    -0.07
     intégr
    -0.07
     vécu
    -0.07
     domaine
    -0.07
    域
    -0.07
    cdr
    -0.07
    POSITIVE LOGITS
    人数
    0.15
     Staffing
    0.12
     staffing
    0.11
    Hiring
    0.11
     workforce
    0.11
     hires
    0.10
    Teams
    0.10
     Workforce
    0.10
     crews
    0.10
     troops
    0.10
    Activations Density 0.027%

    No Known Activations