© 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. 44724
    Prev
    Next
    INDEX
    Explanations

    |

    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
     borderline
    -0.08
     ben
    -0.08
     DAS
    -0.08
     openly
    -0.07
     sert
    -0.07
    _v
    -0.07
     vivo
    -0.07
    anic
    -0.07
    uma
    -0.07
     Kum
    -0.07
    POSITIVE LOGITS
     الخط
    0.08
    �
    0.08
    vq
    0.08
     Horr
    0.07
     филь
    0.07
    Tel
    0.07
     بحث
    0.07
     monumental
    0.07
    Gro
    0.07
     pell
    0.07
    Activations Density 0.054%

    No Known Activations