© 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. 45432
    Prev
    Next
    INDEX
    Explanations

    scientific/technical documents

    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
     dungeon
    -0.09
     perceived
    -0.09
     מוז
    -0.08
     anger
    -0.08
     boating
    -0.08
    Bus
    -0.08
     spaceship
    -0.08
    angel
    -0.08
     limp
    -0.08
    ellipse
    -0.08
    POSITIVE LOGITS
     specificity
    0.14
     primers
    0.10
     SNP
    0.10
     Matching
    0.10
     assays
    0.10
     targeting
    0.10
    zyme
    0.10
     antibodies
    0.10
     peptides
    0.09
     melting
    0.09
    Activations Density 0.004%

    No Known Activations