© 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. 1089
    Prev
    Next
    INDEX
    Explanations

    a

    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
    klu
    -0.08
    anke
    -0.08
    alb
    -0.08
     चरण
    -0.07
    Shot
    -0.07
     מור
    -0.07
     falt
    -0.07
     மூ
    -0.07
    orab
    -0.07
     osv
    -0.07
    POSITIVE LOGITS
    Movies
    0.08
     Sponge
    0.08
     deserve
    0.08
    Realm
    0.08
     jig
    0.07
    Fac
    0.07
    先锋
    0.07
     bungalow
    0.07
     [$
    0.07
    덤
    0.07
    Activations Density 0.063%

    No Known Activations