© 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. 95323
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     eclipse
    -0.08
    <?↵
    -0.08
     Eclipse
    -0.07
     juli
    -0.07
     exports
    -0.07
     produkt
    -0.07
     vampire
    -0.07
     innerhalb
    -0.07
     geliefert
    -0.07
    369
    -0.07
    POSITIVE LOGITS
     assembl
    0.09
    organisatie
    0.09
     tashkil
    0.08
    -performing
    0.08
     معرض
    0.08
     organizações
    0.08
    Administr
    0.08
     Ancient
    0.08
    assem
    0.08
    intos
    0.08
    Activations Density 0.000%

    No Known Activations