© 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. 24620
    Prev
    Next
    INDEX
    Explanations

    from

    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
     enables
    -0.09
     plo
    -0.07
    ंग
    -0.07
    原则
    -0.07
    -ng
    -0.07
     mnoho
    -0.07
     spo
    -0.07
     behulp
    -0.07
     inks
    -0.07
     posibil
    -0.07
    POSITIVE LOGITS
     diciendo
    0.08
     Goes
    0.08
    OF
    0.08
    _LOCK
    0.07
     Tark
    0.07
     Being
    0.07
     Now
    0.07
     dizendo
    0.07
     differently
    0.07
     berupa
    0.07
    Activations Density 0.163%

    No Known Activations