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. 98170
    Prev
    Next
    INDEX
    Explanations

    Z

    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
    สล็อต
    -0.09
    สล็อตออนไลน์
    -0.09
     bidang
    -0.08
     Spielautomaten
    -0.08
     tragamonedas
    -0.08
     swes
    -0.08
     ล
    -0.08
    เกมสล็อต
    -0.08
    xml
    -0.08
     ethan
    -0.08
    POSITIVE LOGITS
    abb
    0.10
    erto
    0.08
     pairs
    0.08
    ABB
    0.08
     abb
    0.08
    ystä
    0.08
    _pairs
    0.07
     critical
    0.07
    Scaler
    0.06
    拉
    0.06
    Activations Density 0.000%

    No Known Activations