© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18808
    Prev
    Next
    INDEX
    Explanations

    say "+"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :get
    -0.08
    :"
    -0.08
    :
    -0.08
    :function
    -0.08
    :Get
    -0.08
    へ
    -0.07
    :↵↵
    -0.07
     获取
    -0.07
    .GRAY
    -0.07
     getting
    -0.07
    POSITIVE LOGITS
    likely
    0.11
     likely
    0.10
     таксама
    0.10
     provavelmente
    0.10
     waarschijnlijk
    0.10
     יהיה
    0.10
     بحيث
    0.10
    probably
    0.10
     павін
    0.09
     מספיק
    0.09
    Activations Density 0.031%

    No Known Activations