© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8042
    Prev
    Next
    INDEX
    Explanations

    diseases and immunity

    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
     נער
    -0.09
     pedals
    -0.08
     terrace
    -0.08
    停车
    -0.08
    车型
    -0.08
     дорож
    -0.08
    終了
    -0.08
    議
    -0.08
     scenic
    -0.08
     asfalt
    -0.08
    POSITIVE LOGITS
     иммун
    0.17
     immune
    0.16
     immunity
    0.14
     lymph
    0.14
     immun
    0.13
     Immun
    0.13
    immune
    0.12
     inmun
    0.11
     macroph
    0.11
    免
    0.11
    Activations Density 0.021%

    No Known Activations