© 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. 23-RESID-POST-AA
    11. 47640
    Prev
    Next
    INDEX
    Explanations

    Bi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     biochemical
    -0.08
    fluid
    -0.08
     heißen
    -0.08
     organisatie
    -0.08
     swimmer
    -0.07
    ch
    -0.07
    afety
    -0.07
     biological
    -0.07
     cohort
    -0.07
    avna
    -0.07
    POSITIVE LOGITS
    ode
    0.15
     gebaseerd
    0.13
     기반
    0.12
     आधारित
    0.12
     baseado
    0.11
    oplast
    0.11
    opol
    0.11
    -Based
    0.11
     осн
    0.11
     basado
    0.11
    Activations Density 0.001%

    No Known Activations