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. 111852
    Prev
    Next
    INDEX
    Explanations

    I

    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
     Pom
    -0.08
    豆
    -0.08
    uttaa
    -0.08
     pomo
    -0.07
     jonge
    -0.07
    -0.07
     jeunesse
    -0.07
     kunt
    -0.07
    ecode
    -0.07
     atroc
    -0.07
    POSITIVE LOGITS
     surveillance
    0.08
     rehearsal
    0.08
    न्ह
    0.08
    systems
    0.08
     singles
    0.08
    .System
    0.07
    Wer
    0.07
     systems
    0.07
     niv
    0.07
    Systems
    0.07
    Activations Density 0.001%

    No Known Activations