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. 8607
    Prev
    Next
    INDEX
    Explanations

    grep

    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
     screw
    -0.09
    gifter
    -0.08
     spac
    -0.08
     mortgages
    -0.08
    holder
    -0.08
     quat
    -0.07
     Alc
    -0.07
    vá
    -0.07
     Mans
    -0.07
     repairs
    -0.07
    POSITIVE LOGITS
     grep
    0.14
    -filter
    0.09
    grep
    0.09
    (filter
    0.08
    .filter
    0.08
    (pattern
    0.08
    (regex
    0.08
    .search
    0.08
    .highlight
    0.08
    .Pattern
    0.08
    Activations Density 0.001%

    No Known Activations