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. 45032
    Prev
    Next
    INDEX
    Explanations

    ▼

    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
     cylind
    -0.08
    δα
    -0.08
    ší
    -0.08
    .mount
    -0.08
     voire
    -0.08
    ذي
    -0.08
    stdcall
    -0.07
     légal
    -0.07
     fini
    -0.07
    ëren
    -0.07
    POSITIVE LOGITS
     gets
    0.08
     grav
    0.07
     ''
    ↵
    0.07
     punkt
    0.07
     heating
    0.07
     unsure
    0.07
    0.07
     });
    ↵
    ↵
    0.07
     ger
    0.07
     sounded
    0.07
    Activations Density 0.002%

    No Known Activations