Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 97067
    Prev
    Next
    INDEX
    Explanations

    ż

    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
     SPI
    -0.08
    _private
    -0.08
     PRIVATE
    -0.08
     SIG
    -0.08
     AUS
    -0.08
     private
    -0.08
    -script
    -0.08
     MAN
    -0.07
    Script
    -0.07
     Private
    -0.07
    POSITIVE LOGITS
     عکس
    0.09
    itig
    0.08
    ethod
    0.08
    >{@
    0.08
    磨
    0.08
    otherapeut
    0.08
     voeren
    0.08
    immung
    0.08
     učink
    0.08
    �
    0.08
    Activations Density 0.000%

    No Known Activations