© 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. 12818
    Prev
    Next
    INDEX
    Explanations

    اف

    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
     अंद
    -0.08
     grooves
    -0.08
    Эк
    -0.08
     antibody
    -0.07
    гар
    -0.07
     CRM
    -0.07
    ეკ
    -0.07
    �
    -0.07
    ТИ
    -0.07
     Chak
    -0.07
    POSITIVE LOGITS
     aumentando
    0.08
     FOUND
    0.08
     Loading
    0.08
     maioria
    0.08
     Strong
    0.08
     Worst
    0.08
    loading
    0.07
     Runtime
    0.07
     salaries
    0.07
     Hyper
    0.07
    Activations Density 0.001%

    No Known Activations