© 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. 19-RESID-POST-AA
    11. 102466
    Prev
    Next
    INDEX
    Explanations

    say cc

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	t
    -0.10
    -0.10
     tupe
    -0.10
    -0.10
     manatu
    -0.10
     ટે
    -0.10
     maual
    -0.10
    ­ment
    -0.10
     ট
    -0.10
    անին
    -0.09
    POSITIVE LOGITS
    ccak
    0.10
    zca
    0.10
    caop
    0.10
    ciendo
    0.09
    ccin
    0.09
    seq
    0.09
    cc
    0.09
    cia
    0.09
    argc
    0.09
    ceu
    0.09
    Activations Density 0.075%
    No Known Activations