© 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. 54907
    Prev
    Next
    INDEX
    Explanations

    visa types

    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
     median
    -0.08
     fib
    -0.08
    rud
    -0.07
    heur
    -0.07
     crude
    -0.07
    fuck
    -0.07
     med
    -0.07
     Md
    -0.07
    :bold
    -0.07
     guessed
    -0.07
    POSITIVE LOGITS
    スポ
    0.09
     сопров
    0.09
     URI
    0.08
     accompagné
    0.08
    市場
    0.08
     мотив
    0.08
     accompagn
    0.08
     licenses
    0.08
     issuance
    0.08
     assort
    0.07
    Activations Density 0.006%

    No Known Activations