Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 75930
    Prev
    Next
    INDEX
    Explanations

    chemical extractions

    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
     freeze
    -0.08
     expiration
    -0.08
     departure
    -0.08
     зам
    -0.07
    departure
    -0.07
     stall
    -0.07
     sum
    -0.07
    freeze
    -0.07
     freezing
    -0.07
    impact
    -0.07
    POSITIVE LOGITS
     לצד
    0.09
     sided
    0.09
    یان
    0.09
    -Pacific
    0.09
    层
    0.08
     الجانب
    0.08
     Grenzen
    0.08
     hoofd
    0.08
    -layer
    0.08
    იღ
    0.08
    Activations Density 0.005%

    No Known Activations