© 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. 25243
    Prev
    Next
    INDEX
    Explanations

    musical intervals

    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
    (reinterpret
    -0.09
    贵州
    -0.08
    (order
    -0.08
    _GRAY
    -0.08
    眉
    -0.08
    <Key
    -0.08
    Params
    -0.07
    �
    -0.07
     �
    -0.07
     bière
    -0.07
    POSITIVE LOGITS
    copies
    0.09
     inbox
    0.09
     leaps
    0.08
     copies
    0.08
     Clement
    0.08
     uptake
    0.07
    /cop
    0.07
     abs
    0.07
     Vertical
    0.07
    .vertical
    0.07
    Activations Density 0.004%

    No Known Activations