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. 46829
    Prev
    Next
    INDEX
    Explanations

    Hill

    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
    ností
    -0.08
     Invitational
    -0.08
     sire
    -0.08
     lobbying
    -0.08
     público
    -0.08
     gleich
    -0.08
     donor
    -0.08
    龍
    -0.08
     Delhi
    -0.08
    ค้
    -0.08
    POSITIVE LOGITS
    ach
    0.08
    interpre
    0.08
    interpret
    0.08
     imposs
    0.07
     værd
    0.07
     trat
    0.07
    aru
    0.07
     Hardcore
    0.07
    ("/
    0.07
     interpreting
    0.07
    Activations Density 0.075%

    No Known Activations