© 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. 70178
    Prev
    Next
    INDEX
    Explanations

    seismic

    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
     Karena
    -0.09
     EXT
    -0.08
     열
    -0.08
     janten
    -0.08
     �
    -0.08
    ext
    -0.07
     했
    -0.07
    (ext
    -0.07
     Nast
    -0.07
    なる
    -0.07
    POSITIVE LOGITS
     dermatitis
    0.07
     muscul
    0.07
    dod
    0.07
    iliy
    0.07
     histó
    0.07
     pocas
    0.07
    .bump
    0.07
     dodge
    0.07
    prud
    0.07
    nog
    0.07
    Activations Density 0.002%

    No Known Activations