Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2015
    Prev
    Next
    INDEX
    Explanations

    ::

    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
    <<"
    -0.08
    rch
    -0.07
     >>=
    -0.07
    ificación
    -0.07
     حاضر
    -0.07
     regain
    -0.07
     &'
    -0.07
     iz
    -0.07
    iderman
    -0.07
     Cunningham
    -0.07
    POSITIVE LOGITS
     antip
    0.08
     fon
    0.08
    侣
    0.08
     mø
    0.07
     Languages
    0.07
     кадров
    0.07
    neb
    0.07
     EDGE
    0.07
    颖
    0.07
     roadmap
    0.07
    Activations Density 0.000%

    No Known Activations