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. 45045
    Prev
    Next
    INDEX
    Explanations

    contract severability

    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
     berri
    -0.08
     Asked
    -0.07
     stability
    -0.07
    estock
    -0.07
    είου
    -0.07
     Recycler
    -0.07
     riječ
    -0.07
     Stability
    -0.07
     роста
    -0.07
     thermal
    -0.06
    POSITIVE LOGITS
    HTTPS
    0.08
     Seriously
    0.08
     Bangkok
    0.08
     SHALL
    0.08
    Nimbus
    0.08
     suffers
    0.08
     sincerely
    0.07
    仍
    0.07
     legitimately
    0.07
     는
    0.07
    Activations Density 0.001%

    No Known Activations