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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 47503
    Prev
    Next
    INDEX
    Explanations

    say "ști"

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antan
    -0.09
    utat
    -0.08
     fang
    -0.08
    малар
    -0.08
    uland
    -0.08
    vall
    -0.08
     konst
    -0.08
    enten
    -0.08
    ancers
    -0.07
     vermogen
    -0.07
    POSITIVE LOGITS
    ști
    0.16
    şti
    0.13
    ște
    0.12
    ască
    0.11
    şte
    0.10
    よ
    0.09
    ți
    0.08
    Ș
    0.08
     tupe
    0.08
    ješt
    0.07
    Activations Density 0.000%

    No Known Activations