© 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. 787
    Prev
    Next
    INDEX
    Explanations

    align

    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
     reinc
    -0.08
    _hot
    -0.08
    意
    -0.08
     Eddie
    -0.07
    .min
    -0.07
     protég
    -0.07
    iteren
    -0.07
     eras
    -0.07
    hera
    -0.07
     territories
    -0.07
    POSITIVE LOGITS
     Sorte
    0.09
    CPP
    0.08
    /About
    0.08
    >Main
    0.08
    (service
    0.07
    'll
    0.07
     kroner
    0.07
     Cerc
    0.07
    ’nde
    0.07
    ,C
    0.07
    Activations Density 0.001%

    No Known Activations