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. 130845
    Prev
    Next
    INDEX
    Explanations

    take

    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
    ormon
    -0.09
    IZER
    -0.08
    érica
    -0.08
    LY
    -0.08
    ति
    -0.08
    सँग
    -0.08
    ADDING
    -0.08
    ॅ
    -0.08
    �运
    -0.08
    िष्ट
    -0.08
    POSITIVE LOGITS
     advantage
    0.21
    aways
    0.17
     ventaja
    0.16
     care
    0.15
    away
    0.14
     Advantage
    0.13
    -home
    0.13
     vantagem
    0.13
     χώρα
    0.13
     soin
    0.12
    Activations Density 0.107%

    No Known Activations