© 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. 103362
    Prev
    Next
    INDEX
    Explanations

    Triangles

    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
    ntil
    -0.09
     afscheid
    -0.09
     MASK
    -0.09
    @Many
    -0.08
     Scope
    -0.08
     ล้าน
    -0.08
    _tracking
    -0.08
     Tracking
    -0.08
     Praça
    -0.08
     Москвы
    -0.08
    POSITIVE LOGITS
     lengths
    0.14
     triangle
    0.13
    Triangle
    0.13
    _triangle
    0.13
     triangles
    0.12
    _lengths
    0.12
     Triangle
    0.12
    Lengths
    0.11
    Triangles
    0.11
    尺寸
    0.11
    Activations Density 0.064%

    No Known Activations