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. 30585
    Prev
    Next
    INDEX
    Explanations

    database backups and downtime

    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
    勇
    -0.09
    ρού
    -0.08
     rebel
    -0.08
    	raw
    -0.08
     obey
    -0.08
    __:
    -0.08
    simpl
    -0.07
    �
    -0.07
    Dice
    -0.07
    _raw
    -0.07
    POSITIVE LOGITS
     downtime
    0.12
     impacts
    0.12
     disruptions
    0.11
     während
    0.10
     disruption
    0.10
     pauses
    0.10
     beein
    0.10
     concurrent
    0.09
     intrusive
    0.09
     concom
    0.09
    Activations Density 0.011%

    No Known Activations