© 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. 63196
    Prev
    Next
    INDEX
    Explanations

    logical reasoning

    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
    Jet
    -0.09
     entrevist
    -0.09
     playlists
    -0.09
    Photos
    -0.08
    _METADATA
    -0.08
     센
    -0.08
     Airport
    -0.08
     photographers
    -0.08
    ethau
    -0.08
    jah
    -0.08
    POSITIVE LOGITS
     premises
    0.13
     Aristotle
    0.10
     premise
    0.10
     rhetoric
    0.09
     deduct
    0.09
     theological
    0.09
     modus
    0.09
     বিশ্বাস
    0.09
     rhetorical
    0.09
     weaken
    0.08
    Activations Density 0.012%

    No Known Activations