© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 5628
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     Forms
    -0.08
    <Select
    -0.08
    (Messages
    -0.08
     DTSTART
    -0.08
     SELECT
    -0.08
     компози
    -0.08
    _REFER
    -0.08
     форму
    -0.08
     GROUP
    -0.07
    	SELECT
    -0.07
    POSITIVE LOGITS
     lej
    0.08
    la
    0.08
    ug
    0.08
     suffice
    0.08
     muk
    0.08
     maxime
    0.07
     kele
    0.07
    illed
    0.07
    are
    0.07
    Pad
    0.07
    Activations Density 0.003%

    No Known Activations