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

    Neuronpedia

    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. 44291
    Prev
    Next
    INDEX
    Explanations

    Transformations and reversals

    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
     repairing
    -0.07
     regul
    -0.07
    еце
    -0.07
     XVIII
    -0.07
     blink
    -0.07
     reducing
    -0.07
     CIS
    -0.07
     ert
    -0.07
     бли
    -0.07
     avi
    -0.07
    POSITIVE LOGITS
    Sim
    0.08
     magique
    0.08
    Contra
    0.08
    .Fatal
    0.08
    Param
    0.08
     occurs
    0.08
    Students
    0.08
    =="
    0.08
     ঘটে
    0.08
     illegally
    0.08
    Activations Density 0.000%

    No Known Activations