© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 30943
    Prev
    Next
    INDEX
    Explanations

    iper

    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
    સાર
    -0.09
    qali
    -0.09
     دین
    -0.08
     қою
    -0.08
    确定
    -0.08
     Intellectual
    -0.08
    (series
    -0.08
     burns
    -0.08
     غ
    -0.08
     opens
    -0.08
    POSITIVE LOGITS
    ccion
    0.08
     विद्यार्थी
    0.08
    ंड
    0.08
     विद्यार्थ
    0.07
     obligatory
    0.07
    학생
    0.07
     NRA
    0.07
     hamm
    0.07
     observe
    0.07
     clearfix
    0.07
    Activations Density 0.001%

    No Known Activations