© 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. 12867
    Prev
    Next
    INDEX
    Explanations

    Below

    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
     হয়ে
    -0.10
     adhesive
    -0.09
    _OPT
    -0.07
     afforded
    -0.07
     হয়ে
    -0.07
    -0.07
     employing
    -0.07
     delicate
    -0.07
    ibição
    -0.07
     remont
    -0.07
    POSITIVE LOGITS
    �
    0.08
     Cobb
    0.08
    hunter
    0.08
    hæ
    0.08
    Hunter
    0.08
     Pant
    0.07
     Verse
    0.07
    Gov
    0.07
     Toch
    0.07
     Vieira
    0.07
    Activations Density 0.005%
    No Known Activations