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. 111692
    Prev
    Next
    INDEX
    Explanations

    Code and formatting characters

    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
     masses
    -0.09
    Against
    -0.08
     eldest
    -0.08
     exams
    -0.07
    397
    -0.07
     messages
    -0.07
    Slave
    -0.07
     путем
    -0.07
     exam
    -0.07
    309
    -0.07
    POSITIVE LOGITS
     वै
    0.08
     효
    0.08
     Breton
    0.08
     soph
    0.08
     Schlaf
    0.08
     אס
    0.08
     أح
    0.07
     اح
    0.07
     sauveg
    0.07
     Oxford
    0.07
    Activations Density 0.000%

    No Known Activations