© 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. 110974
    Prev
    Next
    INDEX
    Explanations

    enneagram

    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
     अभियान
    -0.08
     zeich
    -0.08
    Smarty
    -0.08
     Android
    -0.08
    Android
    -0.08
    Autom
    -0.08
     writ
    -0.07
     perpetual
    -0.07
     Smarty
    -0.07
     spielen
    -0.07
    POSITIVE LOGITS
     bulb
    0.07
     在
    0.07
    Commerce
    0.07
     slender
    0.07
     commerce
    0.07
     OW
    0.07
    عال
    0.07
     orm
    0.07
     �
    0.07
    _sentence
    0.07
    Activations Density 0.000%

    No Known Activations