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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 112349
    Prev
    Next
    INDEX
    Explanations

    up

    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
     forecast
    -0.08
     adjoining
    -0.08
     opposite
    -0.08
     PROC
    -0.07
     plaques
    -0.07
     psicol
    -0.07
     స్పంద
    -0.07
    멀
    -0.07
     crates
    -0.07
     shining
    -0.07
    POSITIVE LOGITS
    掉
    0.16
    弃
    0.10
     voluntarily
    0.09
     aband
    0.09
     abandon
    0.09
     abandoned
    0.09
     abandonment
    0.09
     relinqu
    0.09
     abandoning
    0.09
     bỏ
    0.09
    Activations Density 0.026%

    No Known Activations