© 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. 64527
    Prev
    Next
    INDEX
    Explanations

    Informing someone

    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
     retrofit
    -0.08
    359
    -0.08
    皆
    -0.07
    ৬
    -0.07
     adhesives
    -0.07
     adhesive
    -0.07
     મોડ
    -0.07
     Wild
    -0.07
    ই
    -0.07
    امات
    -0.07
    POSITIVE LOGITS
    oller
    0.09
    (nonatomic
    0.09
     voortdur
    0.08
     adanya
    0.08
     tia
    0.08
    ongo
    0.08
     reservado
    0.08
    nof
    0.08
    :new
    0.08
     отсутств
    0.08
    Activations Density 0.017%

    No Known Activations