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. 23266
    Prev
    Next
    INDEX
    Explanations

    quantum tunneling

    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
     Bradford
    -0.09
    RGB
    -0.09
     RGB
    -0.08
     commentary
    -0.08
    rgb
    -0.08
     QPoint
    -0.08
     Tweet
    -0.08
     dedicado
    -0.08
     adorn
    -0.08
    纸
    -0.08
    POSITIVE LOGITS
     tunn
    0.17
     tunne
    0.15
     tunnel
    0.13
     tunnels
    0.12
     тун
    0.11
     Tunnel
    0.11
     barrier
    0.11
    Barrier
    0.11
    Tunnel
    0.10
     ilegal
    0.10
    Activations Density 0.002%

    No Known Activations