© 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. 78824
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     향
    -0.09
     остат
    -0.08
    oyin
    -0.08
     vot
    -0.08
     સહિત
    -0.08
     GRE
    -0.07
     sog
    -0.07
    Hin
    -0.07
     rearr
    -0.07
    济
    -0.07
    POSITIVE LOGITS
     tandis
    0.11
     whereas
    0.11
    Mozilla
    0.08
     gig
    0.08
     جبکہ
    0.08
     वहीं
    0.07
    Sandbox
    0.07
     Magento
    0.07
    另一方面
    0.07
    .mozilla
    0.07
    Activations Density 0.220%

    No Known Activations