© 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. 97737
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    izie
    -0.08
     solchen
    -0.08
    ဥ
    -0.07
    tructure
    -0.07
    -letter
    -0.07
    -pad
    -0.07
    -negative
    -0.07
    -food
    -0.07
    -e
    -0.07
     ՝
    -0.07
    POSITIVE LOGITS
     forth
    0.08
    ুগ
    0.07
     Again
    0.07
     Uh
    0.07
     mayroon
    0.07
     again
    0.07
    ṣiṣẹ
    0.07
     dessus
    0.07
     दिया
    0.06
    نین
    0.06
    Activations Density 0.339%

    No Known Activations