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. 11-RESID-POST-AA
    6. 75188
    Prev
    Next
    INDEX
    Explanations

    bible verses

    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
     ов
    -0.09
     worst
    -0.09
    Worst
    -0.08
       
    ↵
    -0.08
     Worst
    -0.08
     দুর
    -0.08
    -0.08
    Deviation
    -0.08
    Mother
    -0.08
     deviation
    -0.07
    POSITIVE LOGITS
     ilumin
    0.08
    ினார்
    0.08
     personnels
    0.08
     Información
    0.08
    trib
    0.08
     chem
    0.08
     Hitch
    0.08
     remet
    0.07
     Ikea
    0.07
     Groupe
    0.07
    Activations Density 0.001%

    No Known Activations