© 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. 2785
    Prev
    Next
    INDEX
    Explanations

    Either

    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
     Provides
    -0.08
    esthesia
    -0.08
     voord
    -0.07
     Hui
    -0.07
     Schol
    -0.07
    φή
    -0.07
    ococcus
    -0.07
     Mai
    -0.07
    -full
    -0.07
     mai
    -0.07
    POSITIVE LOGITS
     جور
    0.08
    Cot
    0.08
     contrat
    0.07
     footh
    0.07
     Ohio
    0.07
    纸
    0.07
    hp
    0.07
     sor
    0.07
     piled
    0.07
     pyram
    0.07
    Activations Density 0.001%

    No Known Activations