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. 105975
    Prev
    Next
    INDEX
    Explanations

    Create

    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
     moderated
    -0.08
     lidt
    -0.08
    خفض
    -0.08
    advantages
    -0.07
     снижение
    -0.07
     academia
    -0.07
    sero
    -0.07
    Æ
    -0.07
     engagé
    -0.07
     Ing
    -0.07
    POSITIVE LOGITS
    /open
    0.09
     bunch
    0.08
    堡
    0.08
     forbindelse
    0.08
     ESR
    0.08
     mới
    0.07
    梁
    0.07
     Guardia
    0.07
     कॉल
    0.07
     Kelly
    0.07
    Activations Density 0.021%

    No Known Activations