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. 114099
    Prev
    Next
    INDEX
    Explanations

    Shiva

    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
     giao
    -0.09
     התק
    -0.08
     abge
    -0.08
    _COMM
    -0.08
     liquor
    -0.08
     cientos
    -0.08
    聯
    -0.08
    掛
    -0.08
    _BAL
    -0.08
     Bung
    -0.07
    POSITIVE LOGITS
    armed
    0.09
     devait
    0.09
    developer
    0.08
     પાસે
    0.08
     armed
    0.08
    qualities
    0.08
    нің
    0.08
     possesses
    0.08
    ちは
    0.07
     combinations
    0.07
    Activations Density 0.013%

    No Known Activations