© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68251
    Prev
    Next
    INDEX
    Explanations

    son/sons

    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
     originate
    -0.10
     объем
    -0.09
     originating
    -0.09
     vostra
    -0.08
     agreed
    -0.08
     originates
    -0.08
     செய்யப்பட்ட
    -0.08
     switched
    -0.08
    -det
    -0.07
     volumes
    -0.07
    POSITIVE LOGITS
     inher
    0.12
    继
    0.11
     heirs
    0.10
     heir
    0.09
     inherits
    0.09
     наслед
    0.08
    Fields
    0.08
    们
    0.08
    দের
    0.08
     Zel
    0.08
    Activations Density 0.029%

    No Known Activations