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. 88145
    Prev
    Next
    INDEX
    Explanations

    Unstructured text excerpts

    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
     చేస్తున్నారు
    -0.08
    .reader
    -0.08
     feeder
    -0.08
     korzyst
    -0.07
     inso
    -0.07
     faz
    -0.07
     reader
    -0.07
     vyk
    -0.07
     viewer
    -0.07
     omo
    -0.07
    POSITIVE LOGITS
     пришлось
    0.13
     وكانت
    0.11
     હતો
    0.11
     曾
    0.11
     મેં
    0.11
    曾
    0.11
     당시
    0.10
     surprising
    0.10
    였습니다
    0.10
     colleagues
    0.10
    Activations Density 0.329%

    No Known Activations