© 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 EvalsExportsinterp-engineNEWAPI 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. 110573
    Prev
    Next
    INDEX
    Explanations

    со / во

    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
    malloc
    -0.09
     Jordi
    -0.09
    igen
    -0.08
    થી
    -0.08
    roduction
    -0.08
    jav
    -0.08
     �
    -0.07
     ij
    -0.07
     må
    -0.07
     Koz
    -0.07
    POSITIVE LOGITS
     AP
    0.08
     powers
    0.07
     Φ
    0.07
     Wey
    0.07
    Φ
    0.07
     وس
    0.07
    ίν
    0.07
     Appliance
    0.07
    irr
    0.07
    �
    0.07
    Activations Density 0.009%

    No Known Activations