© 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. 11-RESID-POST-AA
    11. 91554
    Prev
    Next
    INDEX
    Explanations

    th

    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
    anza
    -0.08
    看的
    -0.08
    魂
    -0.08
    bp
    -0.08
     inbound
    -0.08
     punctual
    -0.07
     desped
    -0.07
    -winning
    -0.07
     gereken
    -0.07
     lifting
    -0.07
    POSITIVE LOGITS
     Length
    0.09
    length
    0.09
    evice
    0.09
    _LENGTH
    0.09
     куда
    0.09
    -Length
    0.08
    _lengths
    0.08
    长度
    0.08
    _length
    0.08
     CROSS
    0.08
    Activations Density 0.004%

    No Known Activations