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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29622
    Prev
    Next
    INDEX
    Explanations

    Data and methodology

    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
     secre
    -0.08
    -wise
    -0.08
     killer
    -0.08
     integrar
    -0.07
    corpor
    -0.07
    -efficient
    -0.07
    _WAKE
    -0.07
     integrada
    -0.07
     permitido
    -0.07
     initial
    -0.07
    POSITIVE LOGITS
     provenance
    0.12
     disclaimer
    0.12
     disclaim
    0.11
     credibility
    0.11
     مصدر
    0.10
     Herkunft
    0.10
     происх
    0.10
     biases
    0.10
     originate
    0.10
     источ
    0.10
    Activations Density 0.024%

    No Known Activations