© 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. 11-RESID-POST-AA
    11. 30071
    Prev
    Next
    INDEX
    Explanations

    transistors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     factor
    -0.08
     Cass
    -0.08
    Cass
    -0.08
     venir
    -0.08
     Zuhause
    -0.08
     hafta
    -0.08
     Haushalt
    -0.08
     carrying
    -0.07
    墓
    -0.07
     kashe
    -0.07
    POSITIVE LOGITS
    /files
    0.08
    _threshold
    0.08
     الفرق
    0.08
     sabi
    0.08
    -held
    0.07
    _cond
    0.07
    AMENT
    0.07
     Conditional
    0.07
    -guid
    0.07
     pits
    0.07
    Activations Density 0.001%

    No Known Activations