© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 18464
    Prev
    Next
    INDEX
    Explanations

    my/we

    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
    issaa
    -0.09
    imerkiksi
    -0.09
    обходим
    -0.09
    banyeghị
    -0.08
    ugbọn
    -0.08
    στόσο
    -0.08
    τί
    -0.08
    ੁ
    -0.08
    өнья
    -0.08
    issaat
    -0.08
    POSITIVE LOGITS
    xed
    0.09
    -have
    0.08
     near
    0.08
    xa
    0.08
    -fledged
    0.08
    -like
    0.08
    ishly
    0.08
    -shaped
    0.08
    -your
    0.08
     named
    0.07
    Activations Density 0.009%

    No Known Activations