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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 77424
    Prev
    Next
    INDEX
    Explanations

    Angles

    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
     già
    -0.08
     hotel
    -0.07
    .M
    -0.07
     Motel
    -0.07
     Ram
    -0.07
     Wol
    -0.07
     Kiss
    -0.07
     Ramsey
    -0.07
    .multi
    -0.07
    xn
    -0.07
    POSITIVE LOGITS
     kiri
    0.08
     ТВ
    0.08
     الجميل
    0.08
    ്ഷ
    0.08
     WARNING
    0.08
    bros
    0.08
     AY
    0.08
     toa
    0.08
     тау
    0.08
     kanan
    0.08
    Activations Density 0.005%

    No Known Activations