© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51536
    Prev
    Next
    INDEX
    Explanations

    Top-of-mind awareness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ضاء
    -0.08
     putting
    -0.08
     പ്രക
    -0.08
     प्रकाश
    -0.08
     काही
    -0.08
     pleno
    -0.08
     overw
    -0.08
     संय
    -0.08
    स्व
    -0.07
    बी
    -0.07
    POSITIVE LOGITS
    heap
    0.12
    Heap
    0.11
     heap
    0.11
     Pops
    0.10
     pyramid
    0.10
     Heap
    0.10
     Pyramid
    0.10
     Charts
    0.10
    _heap
    0.09
     naps
    0.09
    Activations Density 0.004%

    No Known Activations