© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 6656
    Prev
    Next
    INDEX
    Explanations

    K

    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
     prenant
    -0.08
     asja
    -0.08
    fé
    -0.08
    czyn
    -0.08
    ჟ
    -0.08
    	Array
    -0.08
    чен
    -0.08
    witz
    -0.08
    גת
    -0.08
    jährige
    -0.08
    POSITIVE LOGITS
    Lastly
    0.09
    orium
    0.09
    odas
    0.08
    antas
    0.08
    ok
    0.08
    oks
    0.08
    and
    0.07
    ārt
    0.07
    aupt
    0.07
    ands
    0.07
    Activations Density 0.000%

    No Known Activations