© 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. 69908
    Prev
    Next
    INDEX
    Explanations

    :

    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
    ME
    -0.08
    од
    -0.07
    tech
    -0.07
    (section
    -0.07
    -tech
    -0.07
    Cog
    -0.07
     ME
    -0.07
    oz
    -0.07
     persever
    -0.07
     compositions
    -0.07
    POSITIVE LOGITS
     헤
    0.08
     Hosted
    0.08
     બેઠ
    0.08
     hepatitis
    0.08
     Bind
    0.07
     Bloody
    0.07
     aquest
    0.07
     років
    0.07
    -mounted
    0.07
     Ard
    0.07
    Activations Density 0.000%

    No Known Activations