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. 11-RESID-POST-AA
    6. 54012
    Prev
    Next
    INDEX
    Explanations

    plot summaries

    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
     میزان
    -0.09
    ונגען
    -0.09
     გახ
    -0.09
     dài
    -0.08
    ינען
    -0.08
     გამოწ
    -0.08
    амҭ
    -0.08
    ვები
    -0.08
     დახ
    -0.08
     նիստ
    -0.08
    POSITIVE LOGITS
     AIDS
    0.09
     violent
    0.09
     suic
    0.09
     violence
    0.08
     frightening
    0.08
     terror
    0.08
     deadly
    0.08
    Joshua
    0.08
     traumat
    0.08
     terrifying
    0.08
    Activations Density 0.072%

    No Known Activations