© 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. 110969
    Prev
    Next
    INDEX
    Explanations

    yoga

    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
     scha
    -0.08
     snug
    -0.08
    باب
    -0.08
     guarding
    -0.08
     els
    -0.08
     reproduc
    -0.07
     الإسلام
    -0.07
     sub
    -0.07
    gaben
    -0.07
     Andal
    -0.07
    POSITIVE LOGITS
    	acc
    0.08
    ，好
    0.08
    ിലും
    0.08
    ൈന
    0.08
     ending
    0.08
     enrol
    0.08
    微软
    0.07
    ಿರುವ
    0.07
    uhn
    0.07
    (--
    0.07
    Activations Density 0.000%

    No Known Activations