© 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. 19-RESID-POST-AA
    11. 102213
    Prev
    Next
    INDEX
    Explanations

    command line arguments

    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
     или
    -0.08
    _Input
    -0.08
     //*
    -0.08
    pexpr
    -0.08
     мыс
    -0.08
     లేదా
    -0.07
    !)
    -0.07
     prepping
    -0.07
     eða
    -0.07
    !),
    -0.07
    POSITIVE LOGITS
     unused
    0.10
    unused
    0.10
    Unused
    0.09
     frequencies
    0.09
     irrelevant
    0.08
     तभी
    0.08
    amanzi
    0.08
     ignored
    0.08
     meaningless
    0.08
     unheard
    0.08
    Activations Density 0.000%

    No Known Activations