© 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. 23-RESID-POST-AA
    11. 97485
    Prev
    Next
    INDEX
    Explanations

    Text encoding/formatting

    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
    phys
    -0.08
    .usermodel
    -0.08
     rins
    -0.07
     arbitration
    -0.07
    lose
    -0.07
    елі
    -0.07
    -global
    -0.07
    Vpc
    -0.07
    917
    -0.07
     positives
    -0.07
    POSITIVE LOGITS
     Markdown
    0.19
     Mermaid
    0.18
     Unicode
    0.18
     unicode
    0.16
     ASCII
    0.16
     La
    0.15
     markdown
    0.15
     ascii
    0.15
     Latex
    0.13
     MARK
    0.13
    Activations Density 0.025%

    No Known Activations