Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 11907
    Prev
    Next
    INDEX
    Explanations

    cryptography, DES algorithm

    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
     notice
    -0.08
     recognise
    -0.08
     quietly
    -0.08
     noticed
    -0.08
    -grey
    -0.08
     nisso
    -0.08
    hra
    -0.08
     phát
    -0.07
     quieter
    -0.07
     realise
    -0.07
    POSITIVE LOGITS
    Barang
    0.09
    ryf
    0.08
    أي
    0.08
    女孩
    0.08
     barang
    0.08
    廷
    0.07
     Tradition
    0.07
    ميس
    0.07
     vik
    0.07
    ultz
    0.07
    Activations Density 0.000%

    No Known Activations