© 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. 96477
    Prev
    Next
    INDEX
    Explanations

    Programming syntax

    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
     Low
    -0.10
    Low
    -0.10
     por
    -0.09
    (Current
    -0.09
    _Current
    -0.09
     Lower
    -0.09
    Lower
    -0.09
     Highly
    -0.09
    (New
    -0.09
    _Local
    -0.09
    POSITIVE LOGITS
    	selected
    0.12
    (selected
    0.12
    	active
    0.12
    (existing
    0.12
    	actual
    0.12
    traditional
    0.12
    	expected
    0.12
    previous
    0.12
    selected
    0.12
    popular
    0.12
    Activations Density 0.083%

    No Known Activations