© 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. 47238
    Prev
    Next
    INDEX
    Explanations

    be

    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
     waxaana
    -0.09
     waxaa
    -0.09
     infatti
    -0.09
     ведь
    -0.08
     क्योंकि
    -0.08
     wuxuu
    -0.08
     mantra
    -0.08
     בד
    -0.08
     सज
    -0.08
     ナ
    -0.08
    POSITIVE LOGITS
     möglichst
    0.12
     possam
    0.09
     somehow
    0.09
     بتوان
    0.09
    有所
    0.09
     puedan
    0.08
     réellement
    0.08
     eff
    0.08
     realized
    0.08
     pueda
    0.08
    Activations Density 0.173%

    No Known Activations