© 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. 49004
    Prev
    Next
    INDEX
    Explanations

    tank guns/sizes

    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
    명의
    -0.09
    'entrée
    -0.09
     משנה
    -0.08
    ’entrée
    -0.08
     Beginning
    -0.08
    'économie
    -0.08
    'article
    -0.08
    	Base
    -0.08
    'île
    -0.08
     début
    -0.08
    POSITIVE LOGITS
    594
    0.08
    759
    0.08
    585
    0.08
    454
    0.08
     armored
    0.08
    517
    0.07
    595
    0.07
    505
    0.07
    597
    0.07
     addressed
    0.07
    Activations Density 0.003%

    No Known Activations