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. 58499
    Prev
    Next
    INDEX
    Explanations

    karma

    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
     från
    -0.10
     חג
    -0.09
     каш
    -0.09
     الزيت
    -0.08
     boissons
    -0.08
     oasis
    -0.08
     יותר
    -0.08
     olje
    -0.08
     овощ
    -0.08
     уют
    -0.08
    POSITIVE LOGITS
     karma
    0.12
     deeds
    0.09
    积分
    0.09
    -cycle
    0.08
     karm
    0.08
     Cycle
    0.08
     Karma
    0.08
     historial
    0.08
     accumulated
    0.08
    .pending
    0.08
    Activations Density 0.007%

    No Known Activations