© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103537
    Prev
    Next
    INDEX
    Explanations

    fiber

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ible
    -0.10
    ally
    -0.09
    ively
    -0.09
    ibilities
    -0.09
    itude
    -0.09
    ês
    -0.09
    iveness
    -0.09
    isement
    -0.09
    siniz
    -0.09
    īst
    -0.08
    POSITIVE LOGITS
     optic
    0.15
    optic
    0.15
    romyalgia
    0.11
    -opt
    0.10
     optics
    0.09
     fibers
    0.09
     strands
    0.09
    质
    0.09
    fiber
    0.09
    balls
    0.09
    Activations Density 0.006%

    No Known Activations