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. 23694
    Prev
    Next
    INDEX
    Explanations

    period

    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
    则
    -0.08
    Dirs
    -0.08
     Seah
    -0.07
    ija
    -0.07
    ijska
    -0.07
     Dx
    -0.07
    ijske
    -0.07
    ijskih
    -0.07
     duż
    -0.07
    Jugador
    -0.07
    POSITIVE LOGITS
     ಆದ
    0.09
     ↵↵
    0.08
    _ws
    0.08
     yearning
    0.08
     عب
    0.08
    0.08
     проник
    0.08
     remarkable
    0.08
    。そして
    0.08
     mere
    0.08
    Activations Density 0.071%

    No Known Activations