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. 60603
    Prev
    Next
    INDEX
    Explanations

    inequality with negative numbers

    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
     probably
    -0.11
     wahrscheinlich
    -0.10
     vermutlich
    -0.10
     probablement
    -0.09
     provavelmente
    -0.09
     probablemente
    -0.09
     waarschijnlijk
    -0.08
     Neal
    -0.08
     ndër
    -0.08
     mindst
    -0.08
    POSITIVE LOGITS
     depending
    0.12
     dependiendo
    0.12
     dependendo
    0.11
    depending
    0.11
    ,例如
    0.09
     durchaus
    0.09
     вполне
    0.09
     Depending
    0.09
    甚至
    0.09
    。例如
    0.08
    Activations Density 0.155%

    No Known Activations