© 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. 647
    Prev
    Next
    INDEX
    Explanations

    distinct

    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
     presumed
    -0.08
     reproduced
    -0.07
     통한
    -0.07
    Forums
    -0.07
     melalui
    -0.07
    Repe
    -0.07
     reprodu
    -0.07
     invaluable
    -0.07
     �
    -0.07
     tiens
    -0.07
    POSITIVE LOGITS
     qq
    0.08
     extravagant
    0.07
     sobren
    0.07
     pyro
    0.07
     cuarto
    0.07
    neros
    0.07
    ान
    0.07
    0.07
    mba
    0.07
    manuel
    0.07
    Activations Density 0.009%
    No Known Activations