© 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. 7-RESID-POST-AA
    11. 881
    Prev
    Next
    INDEX
    Explanations

    secure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _${
    -0.08
    _Out
    -0.07
    oft
    -0.07
     teaser
    -0.07
    يتها
    -0.07
     exteriores
    -0.07
     생활
    -0.07
    )*(
    -0.07
     outdoor
    -0.07
    _out
    -0.07
    POSITIVE LOGITS
     finale
    0.08
    ện
    0.08
     viu
    0.08
     lú
    0.08
     origine
    0.08
     pris
    0.07
     prix
    0.07
     trenta
    0.07
    Ì
    0.07
    �
    0.07
    Activations Density 0.001%

    No Known Activations