© 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. 11-RESID-POST-AA
    6. 47564
    Prev
    Next
    INDEX
    Explanations

    _limits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hoc
    -0.09
     rentrer
    -0.09
     iid
    -0.08
     dok
    -0.08
     condiment
    -0.08
     curry
    -0.08
     Tang
    -0.08
    HING
    -0.08
    ception
    -0.08
     crow
    -0.08
    POSITIVE LOGITS
    .mb
    0.08
    ’o
    0.08
    .o
    0.08
    фта
    0.08
     FW
    0.07
    'g
    0.07
     staf
    0.07
    'o
    0.07
     ಫ
    0.07
    percent
    0.07
    Activations Density 0.259%

    No Known Activations