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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 48071
    Prev
    Next
    INDEX
    Explanations

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

    No Comments

    Negative Logits
    몇
    -0.08
     sytu
    -0.07
    ooter
    -0.07
     morals
    -0.07
     arti
    -0.07
     قار
    -0.07
    எ
    -0.07
     Pob
    -0.07
     நாட்ட
    -0.07
     plural
    -0.07
    POSITIVE LOGITS
     hiệu
    0.16
     mại
    0.13
    weke
    0.09
    heim
    0.09
     inderdaad
    0.08
     करती
    0.08
     carry
    0.08
     चिन
    0.08
     nhận
    0.08
     tehok
    0.08
    Activations Density 0.000%

    No Known Activations