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. 42910
    Prev
    Next
    INDEX
    Explanations

    employee turnover costs

    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
    江
    -0.09
    杭州
    -0.08
    饭
    -0.08
     جائے
    -0.08
    fahrt
    -0.08
     城
    -0.08
    徳
    -0.08
    äne
    -0.08
    furter
    -0.08
    自治区
    -0.08
    POSITIVE LOGITS
     overhead
    0.10
     realloc
    0.09
     churn
    0.09
     costly
    0.09
     onboarding
    0.08
     ON
    0.08
     expensive
    0.08
     reac
    0.08
     SMEs
    0.08
     replace
    0.08
    Activations Density 0.009%

    No Known Activations