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. 78621
    Prev
    Next
    INDEX
    Explanations

    was

    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
     saad
    -0.09
     NSLayout
    -0.08
     ಪ್ರಶ
    -0.08
    "));
    -0.08
    wertung
    -0.08
     ניט
    -0.08
    foundation
    -0.08
    logan
    -0.07
     започ
    -0.07
    ophyll
    -0.07
    POSITIVE LOGITS
     संक्रमित
    0.15
    感染
    0.14
     infection
    0.13
     infect
    0.12
     infected
    0.12
     outbreaks
    0.12
     infections
    0.12
     महामारी
    0.11
     ಸೋಂಕ
    0.11
     contag
    0.11
    Activations Density 0.043%

    No Known Activations