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. 49088
    Prev
    Next
    INDEX
    Explanations

    in

    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
     जन
    -0.07
     বিস
    -0.07
     Frank
    -0.07
     aanvraag
    -0.07
    lift
    -0.07
    liste
    -0.07
     inim
    -0.07
     melan
    -0.07
    तः
    -0.07
     stik
    -0.07
    POSITIVE LOGITS
     caliente
    0.08
    gna
    0.08
     contigo
    0.08
     디
    0.08
     μαζί
    0.08
     conmigo
    0.08
     valu
    0.07
    subset
    0.07
     Mobile
    0.07
     Derrick
    0.07
    Activations Density 0.010%

    No Known Activations