© 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. 6546
    Prev
    Next
    INDEX
    Explanations

    474

    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
    ిగా
    -0.09
    ervol
    -0.08
    LOOK
    -0.08
     Brasil
    -0.08
     conci
    -0.07
    -0.07
    ుగా
    -0.07
    ))(
    -0.07
    INSERT
    -0.07
    (locator
    -0.07
    POSITIVE LOGITS
     આવ
    0.09
     आव
    0.07
     verwarm
    0.07
     warm
    0.07
     დავ
    0.07
     BMW
    0.07
    २०१
    0.07
    ure
    0.07
     компания
    0.07
    inian
    0.07
    Activations Density 0.000%

    No Known Activations