© 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. 78832
    Prev
    Next
    INDEX
    Explanations

    buy

    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
    .datas
    -0.08
     Tong
    -0.07
    -0.07
    Commun
    -0.07
     tongues
    -0.07
     jury
    -0.07
     parach
    -0.07
     Tik
    -0.07
     estará
    -0.07
    _srv
    -0.07
    POSITIVE LOGITS
     premises
    0.08
     premise
    0.08
    ,column
    0.08
    一扫
    0.08
     wymag
    0.07
    odb
    0.07
    ोन
    0.07
    por
    0.07
    ,current
    0.07
    ,item
    0.07
    Activations Density 0.006%
    No Known Activations