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. 9212
    Prev
    Next
    INDEX
    Explanations

    lipid

    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
     tiko
    -0.08
    vena
    -0.08
     متاثر
    -0.08
     įvair
    -0.08
     მსგავსი
    -0.08
     sína
    -0.08
    Seven
    -0.08
     şeýle
    -0.08
     متنوعة
    -0.08
     hivyo
    -0.08
    POSITIVE LOGITS
    ubator
    0.07
     extremely
    0.07
     времен
    0.07
    ил
    0.07
    =null
    0.07
    agraph
    0.07
    quisite
    0.07
     invisible
    0.07
    attachment
    0.07
    0.07
    Activations Density 0.000%

    No Known Activations