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. 58694
    Prev
    Next
    INDEX
    Explanations

    ized

    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
    'ensemble
    -0.08
     जिस
    -0.08
    intern
    -0.07
    ения
    -0.07
     situated
    -0.07
    ’ensemble
    -0.07
     Profession
    -0.07
     Shuttle
    -0.07
     Rh
    -0.07
    я
    -0.07
    POSITIVE LOGITS
     ayuu
    0.11
     ayaa
    0.11
     beware
    0.11
     ayaan
    0.09
    即可
    0.09
     deberá
    0.09
     deserves
    0.09
     prohibits
    0.09
     avrebbe
    0.08
     infatti
    0.08
    Activations Density 0.203%

    No Known Activations