© 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. 69015
    Prev
    Next
    INDEX
    Explanations

    Abstract concepts and descriptions

    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
    =(-
    -0.07
    _gu
    -0.07
     anlam
    -0.07
     demais
    -0.07
     Paulo
    -0.07
    mäß
    -0.07
     respectivos
    -0.07
    Credito
    -0.07
     resp
    -0.07
    se
    -0.07
    POSITIVE LOGITS
     tegelijk
    0.12
    ，包括
    0.11
    都是
    0.11
     подряд
    0.10
    都有
    0.09
    četně
    0.09
    都会
    0.09
     voorkomende
    0.09
    มาย
    0.09
    යක්
    0.09
    Activations Density 0.594%

    No Known Activations