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. 60930
    Prev
    Next
    INDEX
    Explanations

    Sensory details

    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
     �
    -0.10
     Sudan
    -0.09
     eb
    -0.08
    сю
    -0.08
     apolog
    -0.08
     forfe
    -0.07
     Santos
    -0.07
    pu
    -0.07
     सम्म
    -0.07
     Sanctuary
    -0.07
    POSITIVE LOGITS
     autumn
    0.10
    -cut
    0.09
     crisp
    0.09
    空气
    0.09
     الهواء
    0.08
     DIN
    0.08
    மான
    0.08
    洁
    0.08
    -clear
    0.08
     sty
    0.08
    Activations Density 0.005%

    No Known Activations