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. 30702
    Prev
    Next
    INDEX
    Explanations

    bracelets

    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
    Cue
    -0.08
    umb
    -0.08
    大学
    -0.08
     rov
    -0.07
     derby
    -0.07
     과
    -0.07
     ozn
    -0.07
     animate
    -0.07
    TP
    -0.07
     torque
    -0.07
    POSITIVE LOGITS
     biod
    0.09
    essing
    0.08
     Am
    0.08
     probi
    0.07
     Melhor
    0.07
     Kuch
    0.07
     Chanel
    0.07
     Biod
    0.07
     cyst
    0.07
     Perl
    0.07
    Activations Density 0.003%

    No Known Activations