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. 78545
    Prev
    Next
    INDEX
    Explanations

    Mosquitoes and breeding

    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
     알고
    -0.10
     다른
    -0.08
    字体
    -0.08
     买
    -0.08
     스마트
    -0.08
     khách
    -0.07
    หัส
    -0.07
     SOLD
    -0.07
    算法
    -0.07
     curvature
    -0.07
    POSITIVE LOGITS
     ponds
    0.10
    \Database
    0.09
     pudd
    0.09
     reservoirs
    0.09
     lakes
    0.09
    塘
    0.08
     bowls
    0.08
    渠
    0.08
     amateur
    0.08
    \Eloquent
    0.08
    Activations Density 0.016%

    No Known Activations