© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 50168
    Prev
    Next
    INDEX
    Explanations

    Nature, water and light

    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
     erittäin
    -0.12
     വളരെ
    -0.11
     significantly
    -0.11
     nicely
    -0.11
     extremely
    -0.11
     efficacement
    -0.11
     Definitely
    -0.11
     considerably
    -0.11
     exceptionally
    -0.11
     veľmi
    -0.10
    POSITIVE LOGITS
     tasting
    0.10
     laughed
    0.10
     laughing
    0.10
     kissed
    0.10
    —a
    0.10
     आग्रह
    0.10
    孩
    0.10
     perfumes
    0.10
     perfume
    0.10
     sigh
    0.10
    Activations Density 0.121%

    No Known Activations