© 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. 26303
    Prev
    Next
    INDEX
    Explanations

    instructions to language model

    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
     rents
    -0.09
    _CTRL
    -0.09
     Truly
    -0.08
     asap
    -0.08
     ****************************************
    -0.08
    riol
    -0.08
     okum
    -0.08
     réellement
    -0.08
     truly
    -0.08
     someday
    -0.08
    POSITIVE LOGITS
     seemingly
    0.13
     presumably
    0.11
     apparently
    0.11
     seeming
    0.09
     schein
    0.09
     aparentemente
    0.09
     seems
    0.09
     offenbar
    0.08
     stating
    0.08
     seem
    0.08
    Activations Density 0.126%

    No Known Activations