© 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. 70233
    Prev
    Next
    INDEX
    Explanations

    to

    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
     resta
    -0.09
     oversee
    -0.08
     kark
    -0.08
     supervise
    -0.08
     condemn
    -0.07
     ഉപയോഗ
    -0.07
     künst
    -0.07
    onner
    -0.07
     강조
    -0.07
     Wagen
    -0.07
    POSITIVE LOGITS
     occurrence
    0.13
    Occurs
    0.13
     occur
    0.12
    -occ
    0.12
     occurs
    0.11
     occurring
    0.11
     Happens
    0.11
    Occurrence
    0.11
    _occ
    0.10
     wyst
    0.10
    Activations Density 0.066%

    No Known Activations