© 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. 91344
    Prev
    Next
    INDEX
    Explanations

    .app

    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
     landscaping
    -0.08
    ిడ
    -0.08
    kenn
    -0.08
     সামনে
    -0.07
    大会
    -0.07
    entr
    -0.07
    dip
    -0.07
     NASCAR
    -0.07
    itives
    -0.07
     intuit
    -0.07
    POSITIVE LOGITS
     définition
    0.08
     réf
    0.08
     asylum
    0.08
     FRAME
    0.08
     passport
    0.08
    iau
    0.08
     vux
    0.08
    ASH
    0.08
     DEFINE
    0.07
    룸
    0.07
    Activations Density 0.001%

    No Known Activations