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. 23963
    Prev
    Next
    INDEX
    Explanations

    .

    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
    核心
    -0.08
    క్ష
    -0.08
    :↵
    -0.07
    क्ष
    -0.07
    ंभ
    -0.07
    ディース
    -0.07
     основу
    -0.07
    డ్డ
    -0.07
    _cm
    -0.07
    ியல்
    -0.07
    POSITIVE LOGITS
    哪个好
    0.09
     livraison
    0.08
     buenos
    0.08
     delivery
    0.08
     Livraison
    0.08
     Delivery
    0.08
     lenne
    0.08
     ambiguous
    0.08
     seçenek
    0.07
     opción
    0.07
    Activations Density 0.054%

    No Known Activations