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. 43160
    Prev
    Next
    INDEX
    Explanations

    intersection

    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
    Surname
    -0.09
     सच
    -0.08
     �
    -0.08
     justification
    -0.08
     Lah
    -0.08
    TC
    -0.08
    -0.07
    Citation
    -0.07
     distinctions
    -0.07
     Nih
    -0.07
    POSITIVE LOGITS
     skyl
    0.09
     contigo
    0.08
     between
    0.08
    矩
    0.08
     nghiệm
    0.07
     rays
    0.07
    ует
    0.07
     בין
    0.07
     Derm
    0.07
    новение
    0.07
    Activations Density 0.036%

    No Known Activations