© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 23-RESID-POST-AA
    11. 49997
    Prev
    Next
    INDEX
    Explanations

    ipl

    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
    ötet
    -0.08
     erstellt
    -0.08
    oil
    -0.08
     showroom
    -0.08
    浴
    -0.08
     দোক
    -0.07
     Pole
    -0.07
    Pole
    -0.07
     Funnel
    -0.07
     pól
    -0.07
    POSITIVE LOGITS
    랫폼
    0.11
    ATFORM
    0.09
     ios
    0.08
    _platform
    0.08
    platform
    0.08
    Platforms
    0.08
     PLATFORM
    0.08
    -target
    0.08
    atform
    0.08
    evice
    0.08
    Activations Density 0.000%

    No Known Activations