© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 102485
    Prev
    Next
    INDEX
    Explanations

    "second" in other languages

    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
    ತಿಯಿಂದ
    -0.08
    [...,
    -0.08
    ("----------------
    -0.08
    ________________
    -0.08
     ********
    -0.08
    Lastly
    -0.07
     ************************
    -0.07
    สูง
    -0.07
    __________________↵
    -0.07
    ______
    -0.07
    POSITIVE LOGITS
     ikinci
    0.20
     zweite
    0.20
     tweede
    0.20
     second
    0.19
     രണ്ടാം
    0.18
    第二
    0.18
     deuxième
    0.18
     segunda
    0.17
     zweiten
    0.16
     দ্বিত
    0.16
    Activations Density 0.037%

    No Known Activations