© 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. 129550
    Prev
    Next
    INDEX
    Explanations

    function

    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
    oum
    -0.10
     пос
    -0.09
     pasar
    -0.09
     permitted
    -0.08
     ")↵↵
    -0.08
     продав
    -0.08
     SMS
    -0.08
     penas
    -0.08
     troubleshooting
    -0.08
     suspe
    -0.07
    POSITIVE LOGITS
    ینی
    0.08
     الطبية
    0.08
     médic
    0.07
    γει
    0.07
     absolument
    0.07
    稳
    0.07
    van
    0.07
     damn
    0.07
    ading
    0.07
     propres
    0.07
    Activations Density 0.000%

    No Known Activations