© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44900
    Prev
    Next
    INDEX
    Explanations

    address

    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
     camouflage
    -0.09
     Soma
    -0.08
     observe
    -0.08
     Levels
    -0.08
     soma
    -0.08
     dicho
    -0.07
    barkeit
    -0.07
     logic
    -0.07
     Observe
    -0.07
    uttgart
    -0.07
    POSITIVE LOGITS
     informações
    0.08
    付款
    0.08
     cardstock
    0.08
    gegevens
    0.08
     માહિતી
    0.08
     payroll
    0.08
     정보
    0.08
     વિગતો
    0.07
    是谁
    0.07
    ๊
    0.07
    Activations Density 0.021%

    No Known Activations