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. 15-RESID-POST-AA
    6. 191
    Prev
    Next
    INDEX
    Explanations

    Translations of "otherwise"

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Св
    -0.08
     kaikke
    -0.08
     Slov
    -0.08
     occupying
    -0.08
    λών
    -0.08
     llen
    -0.07
     categorized
    -0.07
    λογία
    -0.07
     szó
    -0.07
     veilige
    -0.07
    POSITIVE LOGITS
     otherwise
    0.12
    otherwise
    0.11
    보다
    0.11
     ansonsten
    0.10
     enhances
    0.10
     더욱
    0.10
     보다
    0.10
     autrement
    0.10
     дополн
    0.10
     enhanced
    0.10
    Activations Density 0.212%

    No Known Activations