© 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. 96631
    Prev
    Next
    INDEX
    Explanations

    长

    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
    URA
    -0.09
    gevallen
    -0.09
    ователь
    -0.08
    оз
    -0.08
    वादी
    -0.08
    řed
    -0.08
    urlijke
    -0.08
    одӣ
    -0.08
    _fmt
    -0.08
     utk
    -0.08
    POSITIVE LOGITS
    安
    0.09
    发
    0.09
    征
    0.08
    Em
    0.08
    驱
    0.07
     shelter
    0.07
     Em
    0.07
    Desktop
    0.07
    安市
    0.07
    {{
    0.07
    Activations Density 0.002%

    No Known Activations