Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 1577
    Prev
    Next
    INDEX
    Explanations

    orted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    语
    -0.09
     Umm
    -0.08
     Rong
    -0.08
     Reve
    -0.07
     Paging
    -0.07
     만들어
    -0.07
     Whale
    -0.07
    ele
    -0.07
     Nearly
    -0.07
     Saddam
    -0.07
    POSITIVE LOGITS
     assortment
    0.10
     mix
    0.09
    usion
    0.08
     coats
    0.08
     unt
    0.08
     cables
    0.08
     blend
    0.08
     cable
    0.07
     blends
    0.07
     dress
    0.07
    Activations Density 0.017%

    No Known Activations