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. 1959
    Prev
    Next
    INDEX
    Explanations

    fairy

    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
     tweak
    -0.08
     stimule
    -0.07
    Workbench
    -0.07
     tau
    -0.07
    tun
    -0.07
    િસ
    -0.07
     Hydrogen
    -0.07
    onstr
    -0.07
     חבר
    -0.07
     tun
    -0.07
    POSITIVE LOGITS
     zg
    0.08
    .Feature
    0.08
     चौ
    0.07
     Personas
    0.07
     Caroline
    0.07
    568
    0.07
     Glen
    0.07
     �
    0.07
     simp
    0.07
    оз
    0.07
    Activations Density 0.002%

    No Known Activations