© 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. 19-RESID-POST-AA
    11. 102450
    Prev
    Next
    INDEX
    Explanations

    object height

    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
     միջազգային
    -0.10
     asing
    -0.09
    ’oct
    -0.09
     საერთაშორისო
    -0.09
     enw
    -0.09
     الأجنبية
    -0.09
     suje
    -0.09
    ρωπαϊ
    -0.08
    �ราะห์
    -0.08
     անուն
    -0.08
    POSITIVE LOGITS
    (height
    0.11
    HEIGHT
    0.10
    .height
    0.10
    .Height
    0.10
    _HEIGHT
    0.10
    _height
    0.10
    顶部
    0.10
    Height
    0.09
     HEIGHT
    0.09
     Height
    0.09
    Activations Density 0.005%

    No Known Activations