© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 48558
    Prev
    Next
    INDEX
    Explanations

    Tree in multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lates
    -0.08
     migraine
    -0.08
     Tony
    -0.08
     charger
    -0.08
    -party
    -0.08
    -0.08
     nause
    -0.07
    .Controller
    -0.07
    Tony
    -0.07
     Ducati
    -0.07
    POSITIVE LOGITS
     árboles
    0.30
     árvore
    0.29
     árvores
    0.29
     bomen
    0.29
     arbres
    0.28
     trees
    0.28
     дерево
    0.28
     arbre
    0.28
     дерева
    0.28
    树
    0.27
    Activations Density 0.131%

    No Known Activations