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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 43851
    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
    Listen
    -0.08
    HOOK
    -0.08
    Vu
    -0.08
     Reuters
    -0.08
    Reuters
    -0.08
    -spe
    -0.08
    Listener
    -0.08
    Listeners
    -0.08
     VR
    -0.08
    -hook
    -0.07
    POSITIVE LOGITS
     totaling
    0.18
     કુલ
    0.17
    .total
    0.16
    Subtotal
    0.16
     कुल
    0.16
     totals
    0.15
     TOTAL
    0.15
    TOTAL
    0.15
     মোট
    0.15
     총
    0.15
    Activations Density 0.037%

    No Known Activations