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. 114103
    Prev
    Next
    INDEX
    Explanations

    WiFi

    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
     gape
    -0.08
     unforgettable
    -0.08
     unborn
    -0.08
     glaub
    -0.08
     unfolding
    -0.08
     Mori
    -0.08
     punish
    -0.08
    保
    -0.07
     soaps
    -0.07
    Dear
    -0.07
    POSITIVE LOGITS
     beacon
    0.10
    -enabled
    0.09
    -powered
    0.09
    enabled
    0.08
     Jaz
    0.08
     sn
    0.08
    Harness
    0.07
     enabled
    0.07
     ST
    0.07
     ANT
    0.07
    Activations Density 0.007%

    No Known Activations