© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 20942
    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
    ness
    -0.12
    -ish
    -0.12
    -shaped
    -0.12
     (?)
    -0.12
     (=
    -0.12
    -Based
    -0.12
    -based
    -0.12
     (.
    -0.11
    -to
    -0.11
     etc
    -0.11
    POSITIVE LOGITS
     it
    0.16
     the
    0.16
     there
    0.14
     they
    0.13
     certain
    0.13
     a
    0.13
     these
    0.12
     this
    0.12
     additional
    0.12
     new
    0.12
    Activations Density 0.073%

    No Known Activations