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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 108878
    Prev
    Next
    INDEX
    Explanations

    Travel

    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
    ующие
    -0.08
     slammed
    -0.07
    ующий
    -0.07
    制度
    -0.07
    ующим
    -0.07
    -0.07
     Пу
    -0.07
     prosecution
    -0.07
    ді
    -0.07
     Прич
    -0.07
    POSITIVE LOGITS
     unterwegs
    0.17
     onderweg
    0.16
    Portable
    0.14
     portable
    0.14
     Portable
    0.13
     portátil
    0.13
     campsite
    0.12
     improvis
    0.12
     camping
    0.12
    portable
    0.12
    Activations Density 0.208%

    No Known Activations