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. 111825
    Prev
    Next
    INDEX
    Explanations

    simplified

    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
     Holdings
    -0.08
     embed
    -0.08
    �
    -0.08
     Isl
    -0.08
    فس
    -0.08
    embra
    -0.08
     Samp
    -0.07
     survives
    -0.07
    haltung
    -0.07
    .Persistent
    -0.07
    POSITIVE LOGITS
     להיות
    0.09
     hizo
    0.08
     onderscheiden
    0.08
     maidir
    0.08
    ไม
    0.08
    _DIRECT
    0.08
     makkelijk
    0.08
     напрямую
    0.08
     მიმართ
    0.08
     ziel
    0.07
    Activations Density 0.004%

    No Known Activations