© 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. 23-RESID-POST-AA
    11. 6599
    Prev
    Next
    INDEX
    Explanations

    say "ided"

    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
    ૨૦૧
    -0.09
    -nav
    -0.08
    $ar
    -0.08
    ATING
    -0.08
     thar
    -0.08
    ۱۳۹
    -0.08
    بور
    -0.08
     Regards
    -0.08
    =query
    -0.08
    २०७
    -0.08
    POSITIVE LOGITS
    ided
    0.18
     sided
    0.10
    oded
    0.10
    -sided
    0.10
    iders
    0.09
     complement
    0.09
    leve
    0.09
    iden
    0.08
    째
    0.08
    hooter
    0.08
    Activations Density 0.007%

    No Known Activations