© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54789
    Prev
    Next
    INDEX
    Explanations

    buzzfeed

    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
     Habitat
    -0.08
     Oku
    -0.08
    roku
    -0.08
    qb
    -0.08
     Microsoft
    -0.08
     Jaguars
    -0.08
     Cable
    -0.07
     Toshiba
    -0.07
     Yellowstone
    -0.07
     Clemson
    -0.07
    POSITIVE LOGITS
     novelty
    0.08
     manque
    0.08
    Novel
    0.07
     hä
    0.07
    百科
    0.07
     gesetz
    0.07
     partage
    0.07
     address
    0.07
     ಸೇರಿದಂತೆ
    0.07
     pitfalls
    0.07
    Activations Density 0.012%

    No Known Activations