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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2511
    Prev
    Next
    INDEX
    Explanations

    weight, length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obsess
    -0.08
     vodka
    -0.08
     sinc
    -0.08
    ൈന
    -0.08
     impat
    -0.08
     coping
    -0.07
     cogn
    -0.07
     clever
    -0.07
     yapı
    -0.07
     virtues
    -0.07
    POSITIVE LOGITS
    Neu
    0.09
     Neu
    0.09
    帯
    0.08
    री
    0.08
     rupture
    0.08
    বন্ধ
    0.08
    पट
    0.07
     rupt
    0.07
    ৱ
    0.07
    pix
    0.07
    Activations Density 0.038%

    No Known Activations