© 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. 19-RESID-POST-AA
    11. 102202
    Prev
    Next
    INDEX
    Explanations

    унк

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omed
    -0.08
    acked
    -0.08
    known
    -0.07
     available
    -0.07
     chosen
    -0.07
    rift
    -0.07
    ummi
    -0.07
     liiga
    -0.07
    represented
    -0.07
     तरह
    -0.07
    POSITIVE LOGITS
    цыян
    0.17
    țional
    0.17
    цион
    0.16
    ionali
    0.16
    ional
    0.15
    ціон
    0.15
    jonal
    0.15
    ionale
    0.14
    ionais
    0.13
    цией
    0.13
    Activations Density 0.005%

    No Known Activations