© 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. 64016
    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
    ilig
    -0.07
     velmi
    -0.07
    öhn
    -0.07
    asant
    -0.07
    很
    -0.07
    非常
    -0.07
    mektedir
    -0.07
    ři
    -0.07
     vrlo
    -0.07
    cano
    -0.07
    POSITIVE LOGITS
     governance
    0.08
     spec
    0.08
     invece
    0.08
     مض
    0.08
     spé
    0.07
     supposed
    0.07
     rac
    0.07
     supposedly
    0.07
     Regarding
    0.07
    @One
    0.07
    Activations Density 0.066%

    No Known Activations