© 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. 25011
    Prev
    Next
    INDEX
    Explanations

    fail

    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
     rdr
    -0.09
     PRIMARY
    -0.08
     Primary
    -0.08
     idag
    -0.08
    FACT
    -0.07
    140
    -0.07
     CCR
    -0.07
    主营
    -0.07
     Vere
    -0.07
    215
    -0.07
    POSITIVE LOGITS
    /errors
    0.09
     leaned
    0.09
    _OCCURRED
    0.08
     иннова
    0.08
    =test
    0.08
     invaluable
    0.08
    0.08
    Sil
    0.08
     leaning
    0.08
     embraced
    0.08
    Activations Density 0.009%
    No Known Activations