© 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. 1423
    Prev
    Next
    INDEX
    Explanations

    pioneer

    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
    Strong
    -0.08
     Strong
    -0.07
    strong
    -0.07
    .collection
    -0.07
    тин
    -0.07
     critic
    -0.07
     Martínez
    -0.07
    .mat
    -0.07
    HT
    -0.07
     aigu
    -0.07
    POSITIVE LOGITS
     zs
    0.08
     inland
    0.08
    zaam
    0.07
     여부
    0.07
     foli
    0.07
     �
    0.07
    انه
    0.07
     پزشکی
    0.07
     toet
    0.07
     Iterator
    0.07
    Activations Density 0.025%

    No Known Activations