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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 12343
    Prev
    Next
    INDEX
    Explanations

    Les Miserables, Javert

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     affirm
    -0.09
     plur
    -0.08
     affirmation
    -0.08
    級
    -0.07
    生日
    -0.07
    เลย
    -0.07
     inden
    -0.07
     sincere
    -0.07
     trif
    -0.07
     trifft
    -0.07
    POSITIVE LOGITS
     TOT
    0.08
     practica
    0.07
     դուք
    0.07
     простран
    0.07
     conditions
    0.07
     retrieving
    0.07
    ‌توانید
    0.07
     Aer
    0.07
    .Pr
    0.07
     equilibrium
    0.07
    Activations Density 0.001%

    No Known Activations