© 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. 31547
    Prev
    Next
    INDEX
    Explanations

    possibility

    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
     त्यामुळे
    -0.08
     thereby
    -0.08
    /or
    -0.08
    ivered
    -0.08
     consequently
    -0.08
     eigentlich
    -0.08
    Git
    -0.08
     hence
    -0.08
    Dictionary
    -0.07
     snag
    -0.07
    POSITIVE LOGITS
     entirely
    0.09
     weisen
    0.09
     completely
    0.09
     вообще
    0.08
     вовсе
    0.08
     obsessive
    0.08
     наоборот
    0.08
     совсем
    0.08
     Astrology
    0.08
     simply
    0.08
    Activations Density 0.099%

    No Known Activations