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. 101476
    Prev
    Next
    INDEX
    Explanations

    buttons and customization

    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
     implied
    -0.09
    _TRACE
    -0.08
    _stamp
    -0.08
    approx
    -0.08
    american
    -0.08
     sumin
    -0.08
    正规
    -0.07
    /service
    -0.07
     gelt
    -0.07
     lent
    -0.07
    POSITIVE LOGITS
     Assign
    0.10
    .alias
    0.10
     mappings
    0.10
     configure
    0.10
     Assigned
    0.10
     Configure
    0.09
     eingerichtet
    0.09
     настро
    0.09
     assigning
    0.09
    .configure
    0.09
    Activations Density 0.011%

    No Known Activations