© 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. 23-RESID-POST-AA
    11. 48976
    Prev
    Next
    INDEX
    Explanations

    compatibility

    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
     nümay
    -0.08
     నేపథ్యంలో
    -0.08
     చూప
    -0.08
    яне
    -0.08
     발표
    -0.08
     portrayal
    -0.08
     나타
    -0.08
    巡视
    -0.07
     dargestellt
    -0.07
    posedge
    -0.07
    POSITIVE LOGITS
     kompat
    0.24
     compatibility
    0.23
     compatible
    0.23
     Compatibility
    0.22
     compatibles
    0.22
     Compatible
    0.22
    Compatibility
    0.21
     compat
    0.21
     Compat
    0.21
     adapters
    0.20
    Activations Density 0.092%

    No Known Activations