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

    Neuronpedia

    Jacobian LensNEW
    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. 63925
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     upfront
    -0.09
     населения
    -0.08
     👍
    -0.08
     lin
    -0.08
     налич
    -0.08
     dand
    -0.08
     dyn
    -0.07
     কার্য
    -0.07
     имеется
    -0.07
    ਯ
    -0.07
    POSITIVE LOGITS
    빛
    0.12
     �
    0.11
     longing
    0.11
     majest
    0.10
     etched
    0.10
     पर्व
    0.10
     yearning
    0.10
     कविता
    0.10
     metaph
    0.10
     poetic
    0.09
    Activations Density 0.128%

    No Known Activations