Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9216
    Prev
    Next
    INDEX
    Explanations

    aquariums

    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
    981
    -0.09
    Smarty
    -0.09
     Singleton
    -0.09
    Singleton
    -0.09
     että
    -0.08
    98
    -0.08
    مون
    -0.08
    978
    -0.08
    (des
    -0.08
     jolla
    -0.08
    POSITIVE LOGITS
     Responsible
    0.08
    업
    0.08
     Left
    0.08
     Responsable
    0.07
     Militar
    0.07
     nettoyer
    0.07
     IDM
    0.07
     Others
    0.07
     chú
    0.07
     outros
    0.07
    Activations Density 0.006%

    No Known Activations