© 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. 103582
    Prev
    Next
    INDEX
    Explanations

    say "-"

    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
    .system
    -0.08
    Stepper
    -0.08
     시스템
    -0.08
     सिस्टम
    -0.07
     प्रणाली
    -0.07
    ying
    -0.07
     özel
    -0.07
     STEP
    -0.07
     ప్రత్యేక
    -0.07
     system
    -0.07
    POSITIVE LOGITS
    ებისთვის
    0.10
     coefficients
    0.09
    (coeff
    0.09
    ებზე
    0.09
    ორმ
    0.09
     baino
    0.08
    երից
    0.08
    οδο
    0.08
    们
    0.08
    ოთ
    0.08
    Activations Density 0.021%

    No Known Activations