© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99214
    Prev
    Next
    INDEX
    Explanations

    economic

    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
    -0.09
     IZ
    -0.08
     elementary
    -0.08
     Mercer
    -0.08
     Lee
    -0.08
    _EXTERN
    -0.08
     Gle
    -0.08
    lı
    -0.07
     Managing
    -0.07
     tv
    -0.07
    POSITIVE LOGITS
     downturn
    0.09
    典
    0.08
     owed
    0.08
    0.08
    idle
    0.08
    -business
    0.07
    /business
    0.07
     parag
    0.07
     portrayed
    0.07
     grat
    0.07
    Activations Density 0.025%

    No Known Activations