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. 12196
    Prev
    Next
    INDEX
    Explanations

    Different languages

    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
    995
    -0.08
     pant
    -0.08
     alc
    -0.08
     prat
    -0.07
     overt
    -0.07
     compress
    -0.07
    994
    -0.07
    atcher
    -0.07
     compression
    -0.07
     car
    -0.07
    POSITIVE LOGITS
     refers
    0.14
     என்பது
    0.13
     म्हणजे
    0.11
     hingegen
    0.11
     adalah
    0.10
    」は
    0.10
     bezeichnet
    0.10
     হলো
    0.10
    是一
    0.10
    就是
    0.10
    Activations Density 0.191%

    No Known Activations