Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55610
    Prev
    Next
    INDEX
    Explanations

    motherboards

    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
     constitué
    -0.09
    _segment
    -0.09
    oleg
    -0.08
    segment
    -0.08
    xtəlif
    -0.08
     Vaugh
    -0.07
    -flex
    -0.07
    _el
    -0.07
     വിര
    -0.07
    ್ರೀಯ
    -0.07
    POSITIVE LOGITS
     Intel
    0.09
     motherboard
    0.09
     CUDA
    0.08
     Webcam
    0.08
     ASUS
    0.08
     NVIDIA
    0.08
     SKY
    0.08
     stuffed
    0.08
     FPGA
    0.08
     OUT
    0.08
    Activations Density 0.004%

    No Known Activations