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. 117401
    Prev
    Next
    INDEX
    Explanations

    coexistence

    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
     simp
    -0.08
     fired
    -0.08
     knight
    -0.07
    jr
    -0.07
     pomoc
    -0.07
     Carl
    -0.07
    Lien
    -0.07
     lien
    -0.07
    值
    -0.07
    cycl
    -0.07
    POSITIVE LOGITS
     coexist
    0.16
     peacefully
    0.15
     convivencia
    0.12
     harmonious
    0.10
     harmony
    0.10
    กัน
    0.09
     inhabited
    0.08
     interoper
    0.08
     peaceful
    0.08
     Harmony
    0.08
    Activations Density 0.014%

    No Known Activations