© 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. 15-RESID-POST-AA
    11. 16536
    Prev
    Next
    INDEX
    Explanations

    statement

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    D
    -0.09
     Located
    -0.08
    W
    -0.08
    At
    -0.07
    _Surface
    -0.07
     consejo
    -0.07
    IM
    -0.07
     हस्त
    -0.07
    MR
    -0.07
     protections
    -0.07
    POSITIVE LOGITS
     rather
    0.12
    rather
    0.11
    —it
    0.10
    /use
    0.10
    /int
    0.10
    /us
    0.09
    /question
    0.09
     spoken
    0.09
     albeit
    0.09
    /list
    0.09
    Activations Density 0.006%

    No Known Activations