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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 54090
    Prev
    Next
    INDEX
    Explanations

    right angled

    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
     కొనసాగ
    -0.08
     worldwide
    -0.08
     энерг
    -0.08
     Worldwide
    -0.08
     wereldwijd
    -0.08
     liệu
    -0.07
    ่วง
    -0.07
     ವಿಶ್ವ
    -0.07
     silic
    -0.07
     silica
    -0.07
    POSITIVE LOGITS
     abrupt
    0.09
     básica
    0.08
    _corner
    0.08
     rectangular
    0.08
    pendicular
    0.08
     angled
    0.08
     bulky
    0.08
    ura
    0.07
    mente
    0.07
    -shaped
    0.07
    Activations Density 0.012%

    No Known Activations