© 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. 3-RESID-POST-AA
    11. 13257
    Prev
    Next
    INDEX
    Explanations

    ly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    721
    -0.08
    ontology
    -0.08
     ot
    -0.08
    Ot
    -0.08
     Ot
    -0.07
    706
    -0.07
    644
    -0.07
    �
    -0.07
    Soc
    -0.07
    =====
    -0.07
    POSITIVE LOGITS
     firmly
    0.08
    hum
    0.08
     đưa
    0.08
     eng
    0.07
     Edwards
    0.07
     Morton
    0.07
    VL
    0.07
     ka
    0.07
     pillar
    0.07
     자리
    0.07
    Activations Density 0.004%

    No Known Activations