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. 106015
    Prev
    Next
    INDEX
    Explanations

    绪

    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
     Commonwealth
    -0.08
     unbedingt
    -0.08
     Census
    -0.08
    സി
    -0.08
     postage
    -0.07
     தோ
    -0.07
     clad
    -0.07
    કારે
    -0.07
     nozzle
    -0.07
    Penalty
    -0.07
    POSITIVE LOGITS
     emotions
    0.12
     эмоцион
    0.11
     émotions
    0.10
     émotion
    0.10
    绪
    0.10
     moods
    0.10
     emociones
    0.10
     emotional
    0.10
     情
    0.09
     Emotional
    0.09
    Activations Density 0.018%

    No Known Activations