Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 9260
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ionic
    -0.08
    Blueprint
    -0.08
    ě
    -0.08
    ীয়
    -0.08
     tré
    -0.07
     蓝
    -0.07
    _blue
    -0.07
    zeichnen
    -0.07
     काँ
    -0.07
    ిత
    -0.07
    POSITIVE LOGITS
     بغ
    0.08
     ((!
    0.08
    ฝ่าย
    0.08
     برس
    0.08
     antecedentes
    0.08
    formats
    0.07
     Epstein
    0.07
     gedeelte
    0.07
    地主
    0.07
     Comerc
    0.07
    Activations Density 0.002%

    No Known Activations