© 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. 95042
    Prev
    Next
    INDEX
    Explanations

    ama

    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
     Ani
    -0.10
     高清
    -0.09
     Clim
    -0.09
    .TR
    -0.09
     versuchen
    -0.08
     Humane
    -0.08
     murals
    -0.08
     ceremonies
    -0.08
    _ssl
    -0.08
     TECH
    -0.08
    POSITIVE LOGITS
    lake
    0.08
     dull
    0.08
     titt
    0.07
     temporal
    0.07
    estin
    0.07
     wing
    0.07
     insufficient
    0.07
     ficou
    0.07
    াকি
    0.07
     администра
    0.07
    Activations Density 0.000%

    No Known Activations