© 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. 47188
    Prev
    Next
    INDEX
    Explanations

    writing editing

    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
    测速
    -0.09
     VMware
    -0.09
     Félix
    -0.09
     junit
    -0.09
    -installed
    -0.09
     Ned
    -0.09
     Lawn
    -0.09
    缴
    -0.09
     Downloader
    -0.09
     outages
    -0.09
    POSITIVE LOGITS
     revisions
    0.12
     stylist
    0.12
     refinement
    0.11
     storyboard
    0.11
    稿
    0.11
     refining
    0.11
     polishing
    0.10
     수정
    0.10
     tweak
    0.10
     originality
    0.10
    Activations Density 0.078%

    No Known Activations