© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 102655
    Prev
    Next
    INDEX
    Explanations

    Darkness and silence

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     весел
    -0.15
     bubbly
    -0.13
     comedic
    -0.13
     hilarious
    -0.12
     lively
    -0.12
     inflatable
    -0.12
     laughter
    -0.12
     humorous
    -0.12
    欢乐
    -0.12
     amusing
    -0.11
    POSITIVE LOGITS
    冷
    0.12
     hielo
    0.11
     froide
    0.11
     enigmatic
    0.11
    悲
    0.10
     холод
    0.10
     fría
    0.10
     withheld
    0.10
     Assassin
    0.10
    Quiet
    0.10
    Activations Density 0.013%

    No Known Activations