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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 54485
    Prev
    Next
    INDEX
    Explanations

    Alternate historical scenarios

    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
     टिप
    -0.08
     �
    -0.07
     hooked
    -0.07
     dheer
    -0.07
     prefix
    -0.07
    累
    -0.07
     disclaimer
    -0.07
    ागत
    -0.07
     தயார
    -0.07
     yang
    -0.07
    POSITIVE LOGITS
     peacefully
    0.10
     земель
    0.10
     الأراضي
    0.10
     treaties
    0.09
     Pirates
    0.09
    土地
    0.09
    战争
    0.09
     Länder
    0.09
     наступ
    0.09
     prolet
    0.09
    Activations Density 0.016%

    No Known Activations