© 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. 23-RESID-POST-AA
    11. 50904
    Prev
    Next
    INDEX
    Explanations

    �

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     foly
    -0.08
    alcon
    -0.07
     수
    -0.07
     aplicada
    -0.07
    CODE
    -0.07
    jw
    -0.07
    ough
    -0.07
    astră
    -0.07
    수
    -0.07
     pequeña
    -0.07
    POSITIVE LOGITS
    .arm
    0.09
    �
    0.08
    
    0.08
     regenerate
    0.08
     manifested
    0.08
     Fabio
    0.08
    0.08
    .threshold
    0.08
    机
    0.07
     Spitzen
    0.07
    Activations Density 0.000%
    No Known Activations