© 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. 70005
    Prev
    Next
    INDEX
    Explanations

    been

    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
     брат
    -0.08
     guarantees
    -0.08
     भाई
    -0.08
     garantiert
    -0.08
     détour
    -0.08
     забуд
    -0.08
    lymp
    -0.07
    _dev
    -0.07
     гарант
    -0.07
     traceback
    -0.07
    POSITIVE LOGITS
    以来
    0.10
     últ
    0.09
     lately
    0.08
    Desde
    0.08
    Recently
    0.08
     最近
    0.08
     steadily
    0.08
     تناول
    0.08
     Wig
    0.08
    .BL
    0.08
    Activations Density 0.099%

    No Known Activations