© 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. 29196
    Prev
    Next
    INDEX
    Explanations

    cell biology

    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
     soundtrack
    -0.10
     venue
    -0.10
     entertainment
    -0.09
     evenings
    -0.09
     venues
    -0.09
     publicity
    -0.09
    建设
    -0.09
    genres
    -0.09
     automotive
    -0.09
     booked
    -0.08
    POSITIVE LOGITS
     कोश
    0.15
     cells
    0.15
     organisms
    0.14
     células
    0.14
    胞
    0.14
     клетки
    0.13
     apoptosis
    0.13
    .cells
    0.13
     клет
    0.13
     morphology
    0.13
    Activations Density 0.027%

    No Known Activations