© 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. 110752
    Prev
    Next
    INDEX
    Explanations

    Behavior reversal/opposites

    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
     outlets
    -0.09
    akhstan
    -0.08
     vaku
    -0.08
    aket
    -0.08
     IO
    -0.07
    uvat
    -0.07
     mats
    -0.07
     лак
    -0.07
     venues
    -0.07
    ają
    -0.07
    POSITIVE LOGITS
     incompatible
    0.10
     contraind
    0.09
     Both
    0.09
     Gegenteil
    0.08
     Neither
    0.08
     Changes
    0.08
     Whether
    0.08
     impossible
    0.08
    -Compatible
    0.08
    -for
    0.08
    Activations Density 0.002%

    No Known Activations