Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 48450
    Prev
    Next
    INDEX
    Explanations

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

    No Comments

    Negative Logits
     دیگری
    -0.07
    aneously
    -0.07
    oubtedly
    -0.07
    гар
    -0.07
    öhn
    -0.07
    ுண
    -0.07
    awia
    -0.07
    ылар
    -0.07
     olisi
    -0.07
    љ
    -0.07
    POSITIVE LOGITS
     jusqu
    0.63
     hasta
    0.61
     até
    0.61
     hingga
    0.57
     până
    0.56
     μέχρι
    0.54
     Até
    0.53
     έως
    0.52
     до
    0.51
     hanggang
    0.51
    Activations Density 0.089%

    No Known Activations