© 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. 18693
    Prev
    Next
    INDEX
    Explanations

    parameters

    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
     eest
    -0.08
    egiatan
    -0.08
     faaliyet
    -0.07
     Aktivitäten
    -0.07
     Kultur
    -0.07
     attività
    -0.07
     skyscr
    -0.07
     kultura
    -0.07
     Geschichten
    -0.07
     sheets
    -0.07
    POSITIVE LOGITS
    参数
    0.19
     parâmetros
    0.19
     parameters
    0.18
     парамет
    0.18
     parâ
    0.18
     paramètres
    0.17
     параметры
    0.17
    	parameters
    0.17
     signature
    0.17
    _parameters
    0.17
    Activations Density 0.022%

    No Known Activations