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. 98311
    Prev
    Next
    INDEX
    Explanations

    الك

    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
    Keywords
    -0.08
     palabras
    -0.07
     పద
    -0.07
     miss
    -0.07
    bh
    -0.07
    astu
    -0.07
     duch
    -0.07
    not
    -0.07
     egal
    -0.07
     SAG
    -0.07
    POSITIVE LOGITS
    لية
    0.13
    املة
    0.13
    ل
    0.12
    ು
    0.11
    ر
    0.10
    مية
    0.09
    הילה
    0.09
    لى
    0.09
    வ
    0.09
    ామ్
    0.09
    Activations Density 0.001%

    No Known Activations