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. 90295
    Prev
    Next
    INDEX
    Explanations

    on

    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
     Corona
    -0.08
     Wonderful
    -0.08
     Subscribers
    -0.08
     Guide
    -0.08
     Guia
    -0.08
    (Connection
    -0.07
     Sark
    -0.07
     Personally
    -0.07
     Collins
    -0.07
     southern
    -0.07
    POSITIVE LOGITS
     cushions
    0.08
     antics
    0.08
     రంగ
    0.08
     celebr
    0.08
     hack
    0.08
     slain
    0.07
    ackle
    0.07
     tossed
    0.07
     buffered
    0.07
    sep
    0.07
    Activations Density 0.003%

    No Known Activations