© 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. 71058
    Prev
    Next
    INDEX
    Explanations

    your

    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
     Mub
    -0.09
     tidal
    -0.08
     batteries
    -0.08
    Transit
    -0.08
    Maz
    -0.08
    utc
    -0.08
     intervju
    -0.08
    Liquidity
    -0.08
     ticking
    -0.08
     Gwyn
    -0.08
    POSITIVE LOGITS
     реклам
    0.11
     Canva
    0.10
     Photoshop
    0.10
     JPG
    0.09
     изготовления
    0.09
     Illustrator
    0.09
     printers
    0.09
     Adobe
    0.09
     изготов
    0.09
    .Bitmap
    0.09
    Activations Density 0.048%

    No Known Activations