© 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. 19065
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
     reiter
    -0.09
     similarly
    -0.08
     basis
    -0.08
     reiterated
    -0.08
     loop
    -0.08
     misma
    -0.07
    01
    -0.07
    2
    -0.07
     same
    -0.07
    1
    -0.07
    POSITIVE LOGITS
     কিছু
    0.10
     Algumas
    0.09
     দিয়েছেন
    0.09
    Quelques
    0.09
     Alguns
    0.09
     ollut
    0.08
     Verwaltung
    0.08
     einige
    0.08
     Einige
    0.08
     Mõ
    0.08
    Activations Density 0.002%

    No Known Activations