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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 99315
    Prev
    Next
    INDEX
    Explanations

    lattice

    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
     anesthesia
    -0.09
    zyg
    -0.08
     shortlisted
    -0.08
    itaires
    -0.08
     Wahrheit
    -0.08
     Verm
    -0.08
    Truth
    -0.08
     Yak
    -0.08
     atender
    -0.08
     исполнитель
    -0.08
    POSITIVE LOGITS
    spacing
    0.10
    /grid
    0.09
    .spacing
    0.09
    0.08
     lattice
    0.08
     pitches
    0.08
     spacing
    0.08
     ríg
    0.07
     latt
    0.07
    attice
    0.07
    Activations Density 0.003%
    No Known Activations