© 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. 11-RESID-POST-AA
    11. 113549
    Prev
    Next
    INDEX
    Explanations

    probability sequences

    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
     utilizing
    -0.09
     timbang
    -0.08
     leveraging
    -0.08
     Pablo
    -0.08
     rikt
    -0.08
    tributors
    -0.08
     destined
    -0.08
     naut
    -0.08
    _exports
    -0.08
     učen
    -0.08
    POSITIVE LOGITS
     consecutive
    0.16
     contiguous
    0.15
    连续
    0.14
     sequences
    0.13
     adjacent
    0.13
     consecut
    0.12
    _sequences
    0.11
    secutive
    0.11
     连
    0.11
    Sequences
    0.11
    Activations Density 0.038%

    No Known Activations