© 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. 23-RESID-POST-AA
    11. 47734
    Prev
    Next
    INDEX
    Explanations

    French formal letters

    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
     complexities
    -0.09
    74
    -0.08
     smallest
    -0.08
    transform
    -0.08
    dre
    -0.08
    aiman
    -0.07
    plib
    -0.07
    positive
    -0.07
     invocation
    -0.07
    quisite
    -0.07
    POSITIVE LOGITS
    .fit
    0.12
     YAML
    0.08
     फिट
    0.08
    0.08
     ←
    0.08
    аныя
    0.08
     yacc
    0.08
     ರಸ್ತೆ
    0.08
     воб
    0.07
     fit
    0.07
    Activations Density 0.001%

    No Known Activations