© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70188
    Prev
    Next
    INDEX
    Explanations

    negative opinions

    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
    ,and
    -0.07
     EMS
    -0.07
    +,
    -0.07
    nymi
    -0.07
     gelief
    -0.07
    oor
    -0.07
     junho
    -0.07
    ntag
    -0.07
    mehr
    -0.07
    vei
    -0.07
    POSITIVE LOGITS
    .assert
    0.08
    िरी
    0.08
     подбор
    0.08
    _corner
    0.08
    éros
    0.08
    �
    0.08
    忽
    0.08
     someone's
    0.08
     Hauses
    0.08
     overlooks
    0.08
    Activations Density 0.086%

    No Known Activations