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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 24677
    Prev
    Next
    INDEX
    Explanations

    computer file systems

    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
     Englisch
    -0.10
     Airt
    -0.09
     переб
    -0.09
     airfare
    -0.09
     utter
    -0.08
     영어
    -0.08
    英语
    -0.08
     DEAL
    -0.08
    EUR
    -0.07
     英
    -0.07
    POSITIVE LOGITS
    (uid
    0.09
    Neither
    0.08
    Uid
    0.08
    .uid
    0.08
    (spec
    0.08
     inode
    0.08
    (errno
    0.08
    Permissions
    0.08
     rare
    0.08
    PECIAL
    0.08
    Activations Density 0.004%

    No Known Activations