© 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. 96533
    Prev
    Next
    INDEX
    Explanations

    large

    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
     gjin
    -0.07
    cej
    -0.07
    ógicos
    -0.07
     ezint
    -0.07
    stof
    -0.07
    etter
    -0.07
     ratione
    -0.07
    adie
    -0.07
     dìreach
    -0.07
    本网
    -0.07
    POSITIVE LOGITS
     large
    0.62
     huge
    0.58
    large
    0.55
    Large
    0.50
    _large
    0.50
     Large
    0.49
     enormous
    0.49
     große
    0.49
     grote
    0.48
     വലിയ
    0.48
    Activations Density 0.757%

    No Known Activations