© 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. 23-RESID-POST-AA
    11. 97552
    Prev
    Next
    INDEX
    Explanations

    Period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fact
    -0.08
     Sle
    -0.08
    fahr
    -0.08
     вещ
    -0.08
    -à
    -0.08
    -sac
    -0.08
     attracts
    -0.08
     adopts
    -0.07
    768
    -0.07
     faf
    -0.07
    POSITIVE LOGITS
     اجازه
    0.08
     understand
    0.08
     Beginning
    0.08
     familiarize
    0.08
    Eventually
    0.07
    umiem
    0.07
     irgendwann
    0.07
    They
    0.07
     mocked
    0.07
     Unauthorized
    0.07
    Activations Density 0.001%

    No Known Activations