© 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. 7-RESID-POST-AA
    11. 1339
    Prev
    Next
    INDEX
    Explanations

    Removing something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autent
    -0.07
    รุ
    -0.07
    .googleapis
    -0.07
    ，到
    -0.07
     अपर
    -0.07
     오류
    -0.07
     independ
    -0.07
     authent
    -0.07
     গুরুত্ব
    -0.07
     eco
    -0.07
    POSITIVE LOGITS
     carving
    0.11
    掉
    0.11
     protr
    0.10
     carved
    0.09
     rectangular
    0.09
     Geschenk
    0.09
     perfor
    0.09
     taart
    0.09
    面积
    0.09
    Thickness
    0.08
    Activations Density 0.021%

    No Known Activations