© 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. 22103
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     operacional
    -0.07
     මෙම
    -0.07
     cherished
    -0.07
     encaps
    -0.07
    nera
    -0.07
     these
    -0.07
     vaikut
    -0.07
     beloved
    -0.07
     forthcoming
    -0.07
     objet
    -0.07
    POSITIVE LOGITS
    まず
    0.10
    начала
    0.09
     let's
    0.09
     сначала
    0.09
    Let's
    0.09
     zunächst
    0.09
     먼저
    0.08
     calculators
    0.08
    ations
    0.08
     попробовать
    0.08
    Activations Density 0.009%

    No Known Activations