© 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. 23-RESID-POST-AA
    11. 47838
    Prev
    Next
    INDEX
    Explanations

    Programming code file operations

    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
     serez
    -0.10
     слаб
    -0.09
     смесь
    -0.09
     surtout
    -0.08
    rait
    -0.08
    ptom
    -0.08
     aurez
    -0.08
     définition
    -0.08
    uggestion
    -0.08
     nawet
    -0.08
    POSITIVE LOGITS
    .ok
    0.10
    -ok
    0.08
     ok
    0.08
    )||(
    0.08
    Trap
    0.08
    (ok
    0.08
    .tap
    0.08
     OK
    0.08
    	ok
    0.08
     OR
    0.07
    Activations Density 0.001%

    No Known Activations