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. 54064
    Prev
    Next
    INDEX
    Explanations

    copay

    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
    ாப
    -0.07
     سف
    -0.07
     सें
    -0.07
     selber
    -0.07
     Aber
    -0.07
     refractory
    -0.07
     aprofund
    -0.07
     Bish
    -0.07
     deeper
    -0.07
     Abril
    -0.07
    POSITIVE LOGITS
    ركات
    0.09
    فعال
    0.08
    يديو
    0.08
    ukkut
    0.08
    ვან
    0.08
     legit
    0.08
    ових
    0.08
    enja
    0.08
    ينية
    0.08
     loku
    0.08
    Activations Density 0.001%

    No Known Activations