© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13270
    Prev
    Next
    INDEX
    Explanations

    cultivated

    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
    Ana
    -0.09
    辅
    -0.09
     Ana
    -0.09
     Ari
    -0.07
    Rah
    -0.07
     signo
    -0.07
     digitally
    -0.07
     tina
    -0.07
    SIGN
    -0.07
     who's
    -0.07
    POSITIVE LOGITS
     Town
    0.08
     سد
    0.08
     Trip
    0.08
     Thom
    0.07
    ٰ
    0.07
    .serialize
    0.07
     Marion
    0.07
    43
    0.07
     doubling
    0.07
     fib
    0.07
    Activations Density 0.001%

    No Known Activations