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. 111842
    Prev
    Next
    INDEX
    Explanations

    Describing content

    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
    olog
    -0.08
    bottom
    -0.08
     spotlight
    -0.07
    umbersome
    -0.07
    heard
    -0.07
     kullan
    -0.07
     Brigade
    -0.07
     Spotlight
    -0.07
    ceptor
    -0.07
    lenge
    -0.07
    POSITIVE LOGITS
    旨
    0.10
     предназнач
    0.10
     essentiellement
    0.09
     bedoeld
    0.09
     revolve
    0.09
    .intent
    0.08
     intenta
    0.08
    Basically
    0.08
     revolves
    0.08
     depicting
    0.08
    Activations Density 0.091%

    No Known Activations