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. 58316
    Prev
    Next
    INDEX
    Explanations

    Co-working spaces

    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
     después
    -0.09
     यही
    -0.09
     vaginal
    -0.08
     escog
    -0.08
     efectuar
    -0.08
     Wikipedia
    -0.08
     maternal
    -0.08
     contrace
    -0.08
     dieses
    -0.08
     neuronal
    -0.07
    POSITIVE LOGITS
     leasing
    0.09
     turnkey
    0.09
     breakout
    0.08
     fintech
    0.08
     amenities
    0.08
    �
    0.08
    ®
    0.08
     tech
    0.08
     корпоратив
    0.08
     flexibel
    0.08
    Activations Density 0.026%

    No Known Activations