© 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. 2891
    Prev
    Next
    INDEX
    Explanations

    Erosion, coast, or land reclamation

    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
     تب
    -0.08
     исп
    -0.08
     Engels
    -0.08
     Unidade
    -0.08
    情色
    -0.08
    舞
    -0.08
     aliqu
    -0.08
     Quelle
    -0.07
     ইত
    -0.07
    ия
    -0.07
    POSITIVE LOGITS
     stake
    0.08
     shoreline
    0.08
     hills
    0.08
     vise
    0.08
     naturais
    0.08
     walls
    0.08
    Stake
    0.08
    Walls
    0.07
    坡
    0.07
     bulld
    0.07
    Activations Density 0.053%

    No Known Activations