© 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. 54406
    Prev
    Next
    INDEX
    Explanations

    ange

    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
     dre
    -0.07
    ોદ
    -0.07
    -et
    -0.07
     schwarze
    -0.07
    Tu
    -0.07
    டி
    -0.07
     kernel
    -0.07
     kernels
    -0.07
    -fire
    -0.07
    -0.07
    POSITIVE LOGITS
     valori
    0.09
     Philosoph
    0.09
    irlər
    0.08
    wyll
    0.08
     NSInteger
    0.08
    ########################################################################
    0.08
     Liam
    0.08
     circunstancias
    0.08
    qtis
    0.08
    #+
    0.08
    Activations Density 0.000%

    No Known Activations