© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 99503
    Prev
    Next
    INDEX
    Explanations

    RPG hit points

    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
     religioso
    -0.08
     noviembre
    -0.08
    ం
    -0.08
     particulate
    -0.08
     इंग
    -0.08
     Inglaterra
    -0.08
    ρή
    -0.07
     ottobre
    -0.07
     enum
    -0.07
    共享
    -0.07
    POSITIVE LOGITS
    editable
    0.08
     spokoj
    0.08
     daardoor
    0.08
     ڈ
    0.08
    ервые
    0.07
     editable
    0.07
     training
    0.07
    Delta
    0.07
     disabilities
    0.07
    Training
    0.07
    Activations Density 0.004%

    No Known Activations