© 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. 95507
    Prev
    Next
    INDEX
    Explanations

    sel

    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
     CAGR
    -0.09
     respondents
    -0.09
     colspan
    -0.08
    董
    -0.08
     IELTS
    -0.08
     refundable
    -0.08
     풀
    -0.08
    会议
    -0.08
    ociação
    -0.07
    ergens
    -0.07
    POSITIVE LOGITS
     restrictive
    0.09
    restrict
    0.09
     restricting
    0.09
    restr
    0.08
     rechercher
    0.08
     cops
    0.08
     incompatible
    0.08
     restrictions
    0.08
     havoc
    0.08
    restriction
    0.07
    Activations Density 0.003%

    No Known Activations