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. 7-RESID-POST-AA
    6. 130969
    Prev
    Next
    INDEX
    Explanations

    Still

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Timers
    -0.08
     wk
    -0.08
     wf
    -0.08
    élé
    -0.07
    elem
    -0.07
     Spike
    -0.07
     cái
    -0.07
     উপল
    -0.07
     வெ
    -0.07
     Wanda
    -0.07
    POSITIVE LOGITS
     wondering
    0.08
     जारी
    0.08
     kasta
    0.07
     pertin
    0.07
     Beg
    0.07
     Hagen
    0.07
     demikian
    0.07
     Grü
    0.07
     tricky
    0.07
    heels
    0.07
    Activations Density 0.012%

    No Known Activations