© 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. 3-RESID-POST-AA
    6. 12964
    Prev
    Next
    INDEX
    Explanations

    Brackets and apostrophes

    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
    apost
    -0.08
    硕
    -0.08
     Celt
    -0.08
    owników
    -0.08
     सूचना
    -0.07
    958
    -0.07
     लगे
    -0.07
     veneer
    -0.07
     वै
    -0.07
     misconceptions
    -0.07
    POSITIVE LOGITS
    ми
    0.07
     Hari
    0.07
     onset
    0.07
    meh
    0.07
     Hof
    0.07
     ensemble
    0.07
    Pie
    0.07
    서
    0.07
     Kit
    0.07
     Haw
    0.07
    Activations Density 0.115%

    No Known Activations