© 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. 31003
    Prev
    Next
    INDEX
    Explanations

    reform

    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
    sett
    -0.07
    雄
    -0.07
     settles
    -0.07
     Weeks
    -0.07
     Buena
    -0.07
    structors
    -0.07
    atri
    -0.07
     décid
    -0.07
     PCS
    -0.07
     Pumps
    -0.07
    POSITIVE LOGITS
     della
    0.09
     aproape
    0.08
    ochemical
    0.08
    0.08
     μό
    0.08
     luôn
    0.08
     sinful
    0.08
    arczy
    0.08
     అన్న
    0.07
     gotovo
    0.07
    Activations Density 0.001%
    No Known Activations