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. 113865
    Prev
    Next
    INDEX
    Explanations

    also

    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
     incapable
    -0.08
    ಿಗಳ
    -0.08
     légèrement
    -0.08
    ಿಯಿಂದ
    -0.08
    .snap
    -0.08
    anto
    -0.07
    once
    -0.07
     betaalt
    -0.07
    -large
    -0.07
     Snap
    -0.07
    POSITIVE LOGITS
     OTA
    0.08
     psychological
    0.07
     psychotherapy
    0.07
     messen
    0.07
     WHO
    0.07
     whistle
    0.07
    。また
    0.07
     كۆ
    0.07
     ഉള്
    0.07
     erity
    0.07
    Activations Density 0.187%

    No Known Activations