© 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. 11-RESID-POST-AA
    11. 54556
    Prev
    Next
    INDEX
    Explanations

    been

    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
     blanket
    -0.08
     tang
    -0.08
     lar
    -0.08
    И
    -0.08
    Kim
    -0.08
     Fitch
    -0.07
    파트
    -0.07
     ionic
    -0.07
    erweise
    -0.07
    Ved
    -0.07
    POSITIVE LOGITS
    以来
    0.09
     مؤخ
    0.08
    াকা
    0.08
     unc
    0.08
     �
    0.08
     ringing
    0.08
     They've
    0.08
     courant
    0.08
     Aq
    0.07
    没
    0.07
    Activations Density 0.058%

    No Known Activations