© 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. 18944
    Prev
    Next
    INDEX
    Explanations

    wording

    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
     초기
    -0.08
     ضخ
    -0.08
     Idea
    -0.08
     gigantes
    -0.08
     dla
    -0.07
     fama
    -0.07
     عمليات
    -0.07
     مراحل
    -0.07
     Suppose
    -0.07
     огромное
    -0.07
    POSITIVE LOGITS
     wording
    0.16
     phr
    0.16
     succinct
    0.14
     accurately
    0.14
     sentence
    0.13
     phrase
    0.13
     concise
    0.13
     parap
    0.12
     straightforward
    0.12
     exactly
    0.12
    Activations Density 0.063%

    No Known Activations