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. 48347
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    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
     Insider
    -0.08
     Rowan
    -0.08
     DRO
    -0.07
     Fans
    -0.07
     Supervisor
    -0.07
     sober
    -0.07
     Facilit
    -0.07
     Dex
    -0.07
     جب
    -0.07
     Rupert
    -0.07
    POSITIVE LOGITS
    ization
    0.12
    itation
    0.10
    ism
    0.10
    ification
    0.09
    isation
    0.09
    ology
    0.09
    ments
    0.09
    king
    0.09
    ship
    0.09
    ização
    0.09
    Activations Density 0.803%

    No Known Activations