© 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. 23-RESID-POST-AA
    11. 48236
    Prev
    Next
    INDEX
    Explanations

    blood vessel terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chess
    -0.11
     malware
    -0.11
     Nerd
    -0.11
     cheese
    -0.11
     cheats
    -0.10
     Malware
    -0.10
     chatbot
    -0.10
     halloween
    -0.10
     Cheese
    -0.10
     cheat
    -0.10
    POSITIVE LOGITS
     vascular
    0.49
     arteries
    0.41
     혈
    0.41
    血
    0.40
     रक्त
    0.40
    vascular
    0.40
     сосуд
    0.40
     arterial
    0.39
     blood
    0.39
     artery
    0.39
    Activations Density 0.115%

    No Known Activations