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. 30594
    Prev
    Next
    INDEX
    Explanations

    Descriptive compositions

    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
    )>=
    -0.08
     almeno
    -0.08
    scratch
    -0.08
    .notify
    -0.07
     ubr
    -0.07
     atualmente
    -0.07
     analysed
    -0.07
     notifying
    -0.07
    .scr
    -0.07
     Consent
    -0.07
    POSITIVE LOGITS
    特点
    0.09
     craftsmanship
    0.08
    魅
    0.08
    ുള്ള
    0.08
     جمال
    0.08
    后的
    0.08
     ולה
    0.08
     природ
    0.08
     특징
    0.08
     distinctive
    0.08
    Activations Density 0.017%

    No Known Activations