© 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. 23-RESID-POST-AA
    6. 97782
    Prev
    Next
    INDEX
    Explanations

    linear

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ਿਲ
    -0.08
    _cached
    -0.08
    cached
    -0.08
    responsive
    -0.08
    驗
    -0.08
     released
    -0.07
    released
    -0.07
     certified
    -0.07
     deserted
    -0.07
    acted
    -0.07
    POSITIVE LOGITS
     Linear
    0.12
     linear
    0.11
    Linear
    0.11
     Line
    0.11
    .Linear
    0.10
     LINE
    0.09
     Fourier
    0.09
    -linear
    0.09
    _lin
    0.09
    线
    0.09
    Activations Density 0.001%

    No Known Activations