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. 57
    Prev
    Next
    INDEX
    Explanations

    Non-English

    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
     secure
    -0.07
     tv
    -0.07
     TV
    -0.07
     આપવામાં
    -0.07
     Declare
    -0.07
     Eva
    -0.07
     dada
    -0.07
     Given
    -0.07
    tv
    -0.07
     End
    -0.07
    POSITIVE LOGITS
    _SWAP
    0.09
    ాడ
    0.09
     intuit
    0.09
     confusion
    0.09
    事实上
    0.09
     contrary
    0.09
    édiaire
    0.08
     confusing
    0.08
    ישור
    0.08
     weshalb
    0.08
    Activations Density 0.028%

    No Known Activations