© 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. 110527
    Prev
    Next
    INDEX
    Explanations

    aftercare/post-event

    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
    ERG
    -0.08
    одерж
    -0.08
     autoridad
    -0.07
     вообще
    -0.07
     자체
    -0.07
     Führung
    -0.07
     Qualified
    -0.07
     वरिष्ठ
    -0.07
     Migration
    -0.07
    (load
    -0.07
    POSITIVE LOGITS
     aftermath
    0.22
     afterward
    0.20
     afterwards
    0.20
     pós
    0.17
     after
    0.15
     Afterwards
    0.15
     після
    0.15
     Pós
    0.15
    After
    0.14
     post
    0.14
    Activations Density 0.303%

    No Known Activations