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

    Neuronpedia

    Jacobian LensNEW
    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. 43013
    Prev
    Next
    INDEX
    Explanations

    GPU processing

    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
    �
    -0.09
    כם
    -0.08
     impregn
    -0.08
     carbon
    -0.08
     bitters
    -0.08
     wine
    -0.08
     �
    -0.08
     TYPO
    -0.07
    .Where
    -0.07
     wines
    -0.07
    POSITIVE LOGITS
     massively
    0.11
     paralelo
    0.11
     parallel
    0.10
    _parallel
    0.10
    parallel
    0.10
    Parallel
    0.10
     Parallel
    0.10
     GPUs
    0.09
     heavily
    0.09
     parallèle
    0.08
    Activations Density 0.008%

    No Known Activations