© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95815
    Prev
    Next
    INDEX
    Explanations

    Repeated replacements until one remains

    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
    h
    -0.07
    Doctor
    -0.07
    Off
    -0.07
     off
    -0.07
    Прос
    -0.07
     double
    -0.07
    portun
    -0.07
     axes
    -0.07
     адрес
    -0.07
     \
    -0.07
    POSITIVE LOGITS
    剩
    0.13
    .remaining
    0.11
    remaining
    0.11
     Remaining
    0.10
     remaining
    0.10
     narrowed
    0.10
     reduzir
    0.10
    Remaining
    0.10
     Reduction
    0.10
    _remaining
    0.09
    Activations Density 0.015%

    No Known Activations