© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 31169
    Prev
    Next
    INDEX
    Explanations

    section headers and titles

    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
     Originals
    -0.09
     emperor
    -0.08
    ubr
    -0.08
    Vend
    -0.08
    -original
    -0.08
     originals
    -0.08
    angulo
    -0.07
    Bang
    -0.07
    [val
    -0.07
    łość
    -0.07
    POSITIVE LOGITS
     reproductive
    0.08
     صناعة
    0.08
     tunt
    0.07
     actuellement
    0.07
     gastrointestinal
    0.07
     sexual
    0.07
     vezi
    0.07
     workplace
    0.07
     tegenwoordig
    0.07
     vak
    0.07
    Activations Density 0.287%

    No Known Activations