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. 60709
    Prev
    Next
    INDEX
    Explanations

    Math problems

    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
     establecimiento
    -0.08
     scal
    -0.07
     feme
    -0.07
    efs
    -0.07
     Establish
    -0.07
     siano
    -0.07
     respir
    -0.07
     paš
    -0.07
    Inactive
    -0.07
     establishment
    -0.07
    POSITIVE LOGITS
     likewise
    0.09
     honn
    0.08
     المجالات
    0.07
     Guil
    0.07
    há
    0.07
     ether
    0.07
    _REPLY
    0.07
     الإج
    0.07
     mur
    0.07
     хороший
    0.07
    Activations Density 0.049%

    No Known Activations