© 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. 3-RESID-POST-AA
    11. 1475
    Prev
    Next
    INDEX
    Explanations

    solution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.08
     Urs
    -0.08
     Brid
    -0.08
     Mara
    -0.08
     Brook
    -0.08
     Buchanan
    -0.07
     elle
    -0.07
     Soll
    -0.07
     �
    -0.07
    ات
    -0.07
    POSITIVE LOGITS
     cantor
    0.09
    Units
    0.08
    Todos
    0.08
    jug
    0.08
    Lien
    0.07
    Aaron
    0.07
    Pic
    0.07
    Todas
    0.07
    617
    0.07
    521
    0.07
    Activations Density 0.004%

    No Known Activations