© 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. 70277
    Prev
    Next
    INDEX
    Explanations

    HTML and screen coordinates

    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
     nucleotide
    -0.08
     laboratory
    -0.08
     phenotype
    -0.07
     honn
    -0.07
     DNA
    -0.07
    =model
    -0.07
     particulars
    -0.07
     alent
    -0.07
     выращ
    -0.07
     fermentation
    -0.07
    POSITIVE LOGITS
     HWND
    0.11
     billboard
    0.10
    RGBA
    0.09
     Canva
    0.09
     लोगो
    0.09
    _Rect
    0.09
     Billboard
    0.09
     Bunifu
    0.09
     Logo
    0.09
    _resize
    0.09
    Activations Density 0.007%

    No Known Activations