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. 60913
    Prev
    Next
    INDEX
    Explanations

    quadr

    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
     سرد
    -0.10
     Jorn
    -0.09
     interdisciplinary
    -0.08
     Forschungs
    -0.08
     جر
    -0.08
     Voices
    -0.08
    	Account
    -0.08
     Andersen
    -0.07
    igration
    -0.07
     গত
    -0.07
    POSITIVE LOGITS
     exhib
    0.08
     dress
    0.08
     input
    0.08
    cev
    0.08
    cek
    0.08
     draw
    0.08
     desenhos
    0.08
     drawer
    0.08
     раза
    0.08
     dibujos
    0.08
    Activations Density 0.008%

    No Known Activations