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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98147
    Prev
    Next
    INDEX
    Explanations

    du

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     udal
    -0.08
     omgang
    -0.08
    -0.08
     amach
    -0.08
     minus
    -0.08
     faz
    -0.08
     nü
    -0.08
    's
    -0.07
     nub
    -0.07
    mium
    -0.07
    POSITIVE LOGITS
     Travail
    0.10
     Quai
    0.10
     Sénégal
    0.09
     Louvre
    0.09
     Prado
    0.09
     Faso
    0.08
     quai
    0.08
     Livre
    0.08
     Gouvernement
    0.08
     Val
    0.08
    Activations Density 0.002%

    No Known Activations