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. 52888
    Prev
    Next
    INDEX
    Explanations

    precision and location

    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
     beobachten
    -0.09
     faca
    -0.09
     bartender
    -0.08
     observes
    -0.08
     Icons
    -0.08
     fairs
    -0.08
    .icons
    -0.08
    .observable
    -0.08
     vakar
    -0.08
    omega
    -0.08
    POSITIVE LOGITS
     GPS
    0.09
     UAV
    0.09
    거리
    0.09
     gps
    0.08
     milliseconds
    0.08
    .Acc
    0.08
    orian
    0.08
     거리
    0.08
    これ
    0.08
     protobuf
    0.08
    Activations Density 0.003%

    No Known Activations