© 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. 111154
    Prev
    Next
    INDEX
    Explanations

    pickup

    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
    突破
    -0.08
    规律
    -0.08
    андар
    -0.08
    (EIF
    -0.08
     nltk
    -0.07
    瑞
    -0.07
     neural
    -0.07
    �
    -0.07
     décr
    -0.07
     éch
    -0.07
    POSITIVE LOGITS
     BBQ
    0.09
     barbe
    0.09
     barbecue
    0.08
     proyect
    0.08
     workmanship
    0.08
     respectable
    0.08
     cargo
    0.08
     CMP
    0.07
    servar
    0.07
    .Context
    0.07
    Activations Density 0.004%

    No Known Activations