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. 49186
    Prev
    Next
    INDEX
    Explanations

    0

    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
     Crowd
    -0.08
     crowd
    -0.08
    231
    -0.08
    347
    -0.08
     هذه
    -0.07
     trenta
    -0.07
     crowdfunding
    -0.07
    क्राउ
    -0.07
     Patron
    -0.07
     مل
    -0.07
    POSITIVE LOGITS
    Logo
    0.09
     Hol
    0.09
    logo
    0.08
     Logo
    0.08
     Obst
    0.08
     Elektro
    0.08
    idol
    0.08
     electricidad
    0.08
     pisos
    0.08
     compan
    0.08
    Activations Density 0.000%

    No Known Activations