© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 31359
    Prev
    Next
    INDEX
    Explanations

    encryption key derivation

    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
     devol
    -0.09
    Department
    -0.09
     department
    -0.08
     disruptions
    -0.08
     offense
    -0.08
     সুযোগ
    -0.08
     econ
    -0.08
     মন্তব্য
    -0.08
     হয়ে
    -0.08
     dept
    -0.08
    POSITIVE LOGITS
     derived
    0.10
     deriv
    0.09
     Conditioning
    0.09
     deriving
    0.09
     derivados
    0.09
     Derived
    0.09
     conditioning
    0.09
     derive
    0.09
     dér
    0.09
    derived
    0.08
    Activations Density 0.004%

    No Known Activations