© 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. 19-RESID-POST-AA
    11. 22689
    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
     stated
    -0.09
     mentioned
    -0.09
    Being
    -0.09
     নামে
    -0.08
    Specified
    -0.08
    Using
    -0.08
    Containing
    -0.08
     द्वारा
    -0.08
     cited
    -0.08
     लागि
    -0.08
    POSITIVE LOGITS
     it's
    0.24
     there's
    0.20
     something
    0.17
     משהו
    0.17
     they
    0.17
     it
    0.17
     things
    0.16
     the
    0.16
     we
    0.16
     there
    0.15
    Activations Density 0.036%

    No Known Activations