© 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. 110214
    Prev
    Next
    INDEX
    Explanations

    Instance

    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
     timetable
    -0.08
     рух
    -0.08
     plane
    -0.07
     rotor
    -0.07
    चक
    -0.07
     deme
    -0.07
     limousine
    -0.07
    Rotor
    -0.07
    chauff
    -0.07
     prosecutor
    -0.07
    POSITIVE LOGITS
    Inside
    0.10
     Inside
    0.09
    芽
    0.09
     داخل
    0.08
    داخل
    0.08
     внутри
    0.08
     Gain
    0.08
    mele
    0.08
    Archive
    0.08
     nesting
    0.08
    Activations Density 0.001%

    No Known Activations