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. 120430
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
     hoy
    -0.08
     saff
    -0.07
     copper
    -0.07
     cake
    -0.07
     योग
    -0.07
     ase
    -0.07
     rei
    -0.07
     coup
    -0.07
     heg
    -0.07
     obsc
    -0.07
    POSITIVE LOGITS
     equation
    0.08
    utsu
    0.08
     arises
    0.08
     వచ్చింది
    0.08
     arose
    0.08
    itera
    0.08
     eliminates
    0.08
     kugira
    0.08
     Agree
    0.08
     let's
    0.07
    Activations Density 0.066%

    No Known Activations