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. 112887
    Prev
    Next
    INDEX
    Explanations

    front

    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
    Ultimate
    -0.08
     counterpart
    -0.08
    195
    -0.07
     downhill
    -0.07
     conver
    -0.07
     lut
    -0.07
     dips
    -0.07
     Concord
    -0.07
    Radar
    -0.07
     converge
    -0.07
    POSITIVE LOGITS
     внимания
    0.10
     সামনে
    0.10
     forefront
    0.09
     mno
    0.09
     Priority
    0.09
     раскры
    0.09
     গুরুত্ব
    0.09
     внимание
    0.09
     Aufmerksamkeit
    0.08
     disney
    0.08
    Activations Density 0.018%

    No Known Activations