© 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. 96336
    Prev
    Next
    INDEX
    Explanations

    say "ка"

    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
    ifico
    -0.09
     하고
    -0.09
    ство
    -0.08
    entos
    -0.08
     하는
    -0.08
     последний
    -0.08
     пор
    -0.08
     инструкции
    -0.07
    ols
    -0.07
     intenção
    -0.07
    POSITIVE LOGITS
    ка
    0.09
    点
    0.08
    Ј
    0.08
    ­na
    0.08
     anthrop
    0.07
    னை
    0.07
    ikations
    0.07
    iq
    0.07
    Ка
    0.07
    анса
    0.07
    Activations Density 0.000%

    No Known Activations