© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-RESID-POST-AA
    11. 1170
    Prev
    Next
    INDEX
    Explanations

    geometry problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pongo
    -0.09
     constat
    -0.08
     siding
    -0.08
    زب
    -0.08
     BEL
    -0.07
    .Pos
    -0.07
     ONLY
    -0.07
     Nouvelle
    -0.07
     spectator
    -0.07
    oca
    -0.07
    POSITIVE LOGITS
    alsex
    0.07
    …。
    0.07
    ו
    0.07
    休
    0.07
    řeb
    0.07
     brightest
    0.07
    urlaub
    0.07
     délic
    0.07
    ada
    0.07
    rust
    0.07
    Activations Density 0.017%

    No Known Activations