© 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. 5635
    Prev
    Next
    INDEX
    Explanations

    say "cited"

    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
     الحقيقة
    -0.09
    	expected
    -0.09
     حقیقت
    -0.08
     indicates
    -0.08
    .expected
    -0.08
     determined
    -0.08
    -0.08
     indication
    -0.08
     Established
    -0.07
     למעשה
    -0.07
    POSITIVE LOGITS
     cited
    0.19
     mentioned
    0.17
     frequently
    0.17
     invoked
    0.16
     citado
    0.16
     repeatedly
    0.16
     featured
    0.16
     quoted
    0.15
     mencion
    0.15
     recurrent
    0.15
    Activations Density 0.075%
    No Known Activations