© 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. 19-RESID-POST-AA
    11. 20649
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _points
    -0.09
    _POINTS
    -0.09
     caminos
    -0.09
    .points
    -0.08
    Points
    -0.08
     cuestiones
    -0.08
    íz
    -0.08
     shaking
    -0.08
    	points
    -0.08
    .codes
    -0.08
    POSITIVE LOGITS
     its
    0.11
     the
    0.11
     their
    0.09
     named
    0.08
    其
    0.08
     ن
    0.08
     this
    0.08
     luid
    0.08
     namely
    0.07
     as
    0.07
    Activations Density 0.000%

    No Known Activations