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. 109311
    Prev
    Next
    INDEX
    Explanations

    portraits

    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
     jackson
    -0.08
     entspricht
    -0.08
    ूर
    -0.08
     innerhalb
    -0.08
     Treasurer
    -0.08
     stof
    -0.08
    .Payment
    -0.08
     مسلمان
    -0.08
    共产
    -0.07
    تمان
    -0.07
    POSITIVE LOGITS
     antics
    0.09
     playful
    0.08
     essence
    0.08
     angled
    0.08
     chase
    0.07
     fluff
    0.07
     whimsical
    0.07
     workshop
    0.07
    HBox
    0.07
     humorous
    0.07
    Activations Density 0.008%

    No Known Activations