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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 98067
    Prev
    Next
    INDEX
    Explanations

    eine

    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
     ఒక
    -0.15
     ಒಂದು
    -0.15
     ஒரு
    -0.14
     een
    -0.14
     isang
    -0.13
     एका
    -0.13
     einer
    -0.13
     ਇੱਕ
    -0.12
     هڪ
    -0.12
     një
    -0.12
    POSITIVE LOGITS
    त्र
    0.13
     Vielzahl
    0.13
    సారి
    0.12
     neue
    0.12
    شنبه
    0.11
     neçə
    0.11
    ત્ર
    0.11
     solche
    0.11
    新的
    0.10
    दम
    0.10
    Activations Density 0.013%

    No Known Activations