© 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. 19-RESID-POST-AA
    11. 18763
    Prev
    Next
    INDEX
    Explanations

    Religious and evangelical texts

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     textures
    -0.09
    _TEXTURE
    -0.09
     Texture
    -0.09
     informal
    -0.08
     texture
    -0.08
     smart
    -0.08
    (texture
    -0.08
    .Texture
    -0.08
     lori
    -0.08
    _Texture
    -0.08
    POSITIVE LOGITS
     evangel
    0.22
    传播
    0.19
     preaching
    0.19
    宣传
    0.18
     प्रचार
    0.17
     preach
    0.16
     evangelical
    0.16
     proclaim
    0.16
     spreading
    0.16
     preached
    0.15
    Activations Density 0.032%

    No Known Activations