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. 11-RESID-POST-AA
    6. 58376
    Prev
    Next
    INDEX
    Explanations

    image generation

    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
     Atom
    -0.07
     stress
    -0.07
     Pi
    -0.07
     rotor
    -0.07
     toinen
    -0.07
    .atom
    -0.07
     Perd
    -0.07
     bé
    -0.07
     perd
    -0.06
     Romeo
    -0.06
    POSITIVE LOGITS
     ನಿರ್ದೇಶ
    0.10
    ائڻ
    0.09
    Titel
    0.09
     დირექტ
    0.09
     toevoeg
    0.08
     پڻ
    0.08
    Mention
    0.08
     გენ
    0.08
    标题
    0.08
     российских
    0.08
    Activations Density 0.008%

    No Known Activations