© 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. 15-RESID-POST-AA
    11. 16529
    Prev
    Next
    INDEX
    Explanations

    parentheses

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _Map
    -0.07
     prostor
    -0.07
     antid
    -0.07
    izzle
    -0.07
     pyramid
    -0.07
    文本
    -0.07
     PIR
    -0.07
    Pir
    -0.07
     equivalent
    -0.07
    是多少
    -0.07
    POSITIVE LOGITS
     ಅವರು
    0.10
     அவர்கள்
    0.09
     അവർ
    0.09
     they
    0.09
     Queens
    0.09
     Mereka
    0.09
     उन्होंने
    0.09
     они
    0.09
     તેઓ
    0.08
    leister
    0.08
    Activations Density 0.009%

    No Known Activations