© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 5525
    Prev
    Next
    INDEX
    Explanations

    say "antly"

    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
    gebnis
    -0.09
     inoxidable
    -0.09
    folger
    -0.08
    ႈ
    -0.08
     output
    -0.08
    	output
    -0.08
    ۶
    -0.08
    ည္း
    -0.08
    շտ
    -0.08
    	up
    -0.07
    POSITIVE LOGITS
    unately
    0.21
    antly
    0.20
    ation
    0.19
    /export
    0.19
    ància
    0.16
    aciones
    0.15
    ación
    0.15
    ância
    0.14
    ances
    0.14
     khẩu
    0.14
    Activations Density 0.019%

    No Known Activations