© 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. 3-RESID-POST-AA
    11. 13017
    Prev
    Next
    INDEX
    Explanations

    ate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     julg
    -0.08
     бут
    -0.08
    jø
    -0.08
     rum
    -0.08
     cant
    -0.07
    Rn
    -0.07
     Tommy
    -0.07
     infra
    -0.07
     mutual
    -0.07
    엄
    -0.07
    POSITIVE LOGITS
     ಬೇ
    0.08
    0.08
     BCrypt
    0.07
    日は
    0.07
     BOOST
    0.07
     Ken
    0.07
     Monk
    0.07
    tier
    0.07
     tiled
    0.07
    heli
    0.07
    Activations Density 0.003%
    No Known Activations