Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 65171
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    érir
    -0.08
    רט
    -0.08
     տ
    -0.08
    ــ
    -0.07
    큰
    -0.07
     գ
    -0.07
    =\'
    -0.07
     ';
    ↵
    -0.07
    USE
    -0.07
     faudrait
    -0.07
    POSITIVE LOGITS
     прот
    0.08
     同
    0.08
     again
    0.08
     उसी
    0.07
     prijs
    0.07
     same
    0.07
     abay
    0.07
     vergelijk
    0.07
     submitted
    0.07
     επι
    0.07
    Activations Density 0.114%

    No Known Activations