© 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. 129429
    Prev
    Next
    INDEX
    Explanations

    barycentric coordinates

    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
     assault
    -0.11
     assaults
    -0.09
    Funcs
    -0.09
     tango
    -0.09
     Assault
    -0.08
     clazz
    -0.08
     assaulted
    -0.08
    Gatt
    -0.08
     fest
    -0.08
     fashions
    -0.08
    POSITIVE LOGITS
     proportional
    0.10
    比例
    0.10
     proportions
    0.09
     Anteil
    0.09
     Jezus
    0.09
     procent
    0.08
     ശതമ
    0.08
    ịt
    0.08
     proporcional
    0.08
     그래서
    0.08
    Activations Density 0.005%

    No Known Activations