© 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. 492
    Prev
    Next
    INDEX
    Explanations

    essay

    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
    >↵↵
    -0.07
     descr
    -0.07
    -go
    -0.07
     Amenities
    -0.07
     Minis
    -0.07
    -at
    -0.07
    Svc
    -0.07
    .matches
    -0.07
    ,:,:
    -0.07
    ,min
    -0.07
    POSITIVE LOGITS
     writings
    0.11
    哲
    0.11
    《关于
    0.11
     pioneering
    0.10
     hierover
    0.10
     посвящ
    0.10
     فلس
    0.09
     philosophical
    0.09
     rhetoric
    0.09
     اخیر
    0.09
    Activations Density 0.039%

    No Known Activations