© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50086
    Prev
    Next
    INDEX
    Explanations

    ant

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bridges
    -0.08
    úst
    -0.08
    UREMENT
    -0.08
     Jira
    -0.08
     sú
    -0.08
    Global
    -0.08
     vorz
    -0.08
    -Jun
    -0.08
     vault
    -0.08
     curtain
    -0.07
    POSITIVE LOGITS
    ider
    0.20
    IDER
    0.13
    iders
    0.12
    itone
    0.11
    ich
    0.10
    idi
    0.09
    ican
    0.09
    imap
    0.09
    yder
    0.08
    ifer
    0.08
    Activations Density 0.001%

    No Known Activations