© 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. 11-RESID-POST-AA
    11. 75634
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    öse
    -0.08
    Durante
    -0.08
    Cert
    -0.08
    VF
    -0.08
    Mons
    -0.08
    Spectrum
    -0.08
    HF
    -0.08
    span
    -0.08
     అనే
    -0.08
     Rä
    -0.07
    POSITIVE LOGITS
     vali
    0.08
     besta
    0.08
     stuff
    0.08
     yao
    0.07
     modulus
    0.07
     loi
    0.07
     Browns
    0.07
     sonucu
    0.07
     erhöht
    0.07
    黄
    0.07
    Activations Density 0.102%

    No Known Activations