© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 49419
    Prev
    Next
    INDEX
    Explanations

    periods

    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
    aczego
    -0.13
     】↵↵
    -0.09
    ing
    -0.08
     misschien
    -0.08
    atória
    -0.08
     ؟↵↵
    -0.08
     immerhin
    -0.07
    යේ
    -0.07
    ?q
    -0.07
     туралы
    -0.07
    POSITIVE LOGITS
     Therefore
    0.52
     Thus
    0.52
     So
    0.51
     so
    0.50
     thus
    0.50
    Therefore
    0.48
    Thus
    0.47
     therefore
    0.47
     Hence
    0.47
     поэтому
    0.46
    Activations Density 2.437%

    No Known Activations