Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112290
    Prev
    Next
    INDEX
    Explanations

    dislocate

    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
    lywood
    -0.07
    adi
    -0.07
     controlling
    -0.07
     style
    -0.07
     Supp
    -0.07
     stratégie
    -0.07
     Strategy
    -0.06
    ượng
    -0.06
     Ryan
    -0.06
    wj
    -0.06
    POSITIVE LOGITS
     Gelen
    0.09
     نکرد
    0.08
     canine
    0.08
     snapping
    0.08
    /reset
    0.08
     límite
    0.08
     مشک
    0.08
    ировки
    0.08
     intentar
    0.08
     Fahrrad
    0.08
    Activations Density 0.004%

    No Known Activations