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. 19
    Prev
    Next
    INDEX
    Explanations

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

    No Comments

    Negative Logits
    Originally
    -0.08
     originally
    -0.08
     yacc
    -0.08
     специально
    -0.08
     originalmente
    -0.08
     первонач
    -0.07
     następ
    -0.07
    漂亮
    -0.07
     historically
    -0.07
     attorneys
    -0.07
    POSITIVE LOGITS
     malah
    0.11
     మాత్రం
    0.09
    কা
    0.09
     instead
    0.08
    却
    0.08
     �
    0.08
    _OPCODE
    0.08
     ineens
    0.08
     sinister
    0.08
     Gegenteil
    0.08
    Activations Density 0.050%

    No Known Activations