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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12114
    Prev
    Next
    INDEX
    Explanations

    loss

    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
     eftir
    -0.09
    vrd
    -0.08
     반환
    -0.08
     好
    -0.08
     vrij
    -0.08
    -display
    -0.08
    hooter
    -0.08
     vr
    -0.08
     bell
    -0.08
     Ivy
    -0.07
    POSITIVE LOGITS
    失
    0.09
    _fail
    0.09
     실패
    0.09
     misguided
    0.08
     pérdida
    0.08
     perdre
    0.08
     loss
    0.08
     unsuccessful
    0.08
    _loss
    0.08
     unders
    0.08
    Activations Density 0.003%

    No Known Activations