© 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. 70179
    Prev
    Next
    INDEX
    Explanations

    idle

    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
    alez
    -0.08
     кру
    -0.08
    arit
    -0.08
     literal
    -0.07
    anci
    -0.07
    _EXCEPTION
    -0.07
     Linda
    -0.07
     Dam
    -0.07
     gefällt
    -0.07
    Exclusive
    -0.07
    POSITIVE LOGITS
     dormant
    0.12
    闲
    0.10
    তম
    0.09
    暇
    0.09
    的时候
    0.08
     idle
    0.08
     torque
    0.08
    /null
    0.08
     sile
    0.08
     inactivity
    0.08
    Activations Density 0.010%

    No Known Activations