© 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. 8035
    Prev
    Next
    INDEX
    Explanations

    ers

    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
    _GO
    -0.09
    _FATAL
    -0.08
     popcorn
    -0.07
     tubo
    -0.07
    Padding
    -0.07
     remedy
    -0.07
     saying
    -0.07
    ints
    -0.07
    �
    -0.07
     obliga
    -0.07
    POSITIVE LOGITS
     capable
    0.08
    “双
    0.08
     
    0.08
    ataset
    0.07
    (Double
    0.07
    (protocol
    0.07
    ，还有
    0.07
    λέον
    0.07
     فك
    0.07
    Proces
    0.07
    Activations Density 0.000%

    No Known Activations