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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77434
    Prev
    Next
    INDEX
    Explanations

    Cornell note-taking

    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
    pressions
    -0.08
     нел
    -0.07
     št
    -0.07
    usions
    -0.07
    xffffffff
    -0.07
     Ther
    -0.07
    he
    -0.07
    unlink
    -0.07
     phe
    -0.07
    -ins
    -0.07
    POSITIVE LOGITS
     batería
    0.09
     apresentam
    0.09
     estruct
    0.08
    ரி
    0.08
    orney
    0.08
     structured
    0.08
     manera
    0.08
     presentación
    0.08
    住宅
    0.08
    Fila
    0.08
    Activations Density 0.001%

    No Known Activations