© 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. 112448
    Prev
    Next
    INDEX
    Explanations

    yesterday

    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
     Kra
    -0.09
    孔
    -0.08
     grooves
    -0.08
    Broker
    -0.08
     কাপ
    -0.08
     BOR
    -0.07
     smell
    -0.07
     Mustang
    -0.07
    غات
    -0.07
     üy
    -0.07
    POSITIVE LOGITS
     Abend
    0.11
     morning
    0.09
     CM
    0.08
    -Friday
    0.08
     Monday
    0.08
    -day
    0.08
    以来
    0.08
    esterday
    0.08
     Ton
    0.08
    day
    0.08
    Activations Density 0.007%

    No Known Activations