© 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. 8089
    Prev
    Next
    INDEX
    Explanations

    science/neuroscience

    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
     Steam
    -0.08
     pente
    -0.08
     vapeur
    -0.08
     steam
    -0.08
     Pell
    -0.08
     oll
    -0.08
     phosphorylation
    -0.08
     выше
    -0.08
     coax
    -0.08
     Trent
    -0.08
    POSITIVE LOGITS
     neuroscience
    0.11
     neurosc
    0.10
     Neuros
    0.09
     experiments
    0.08
     insights
    0.08
     studies
    0.08
     breakthroughs
    0.08
    Mill
    0.08
    juven
    0.08
     inzichten
    0.08
    Activations Density 0.006%

    No Known Activations