© 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. 79376
    Prev
    Next
    INDEX
    Explanations

    return

    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
    ain
    -0.08
     gur
    -0.08
     almost
    -0.08
    sea
    -0.07
    ோக
    -0.07
     clocks
    -0.07
    uko
    -0.07
    ある
    -0.07
    Almost
    -0.07
     nearly
    -0.07
    POSITIVE LOGITS
     nltk
    0.09
     daraus
    0.09
     пригод
    0.08
     Saying
    0.08
    �
    0.08
    RL
    0.08
    edict
    0.08
    Born
    0.08
     Regulatory
    0.07
    Municip
    0.07
    Activations Density 0.005%

    No Known Activations