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. 52656
    Prev
    Next
    INDEX
    Explanations

    Law

    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
     Twitch
    -0.09
     teammate
    -0.09
     Extras
    -0.09
    �
    -0.08
     camar
    -0.08
    好友
    -0.08
     Kunden
    -0.08
     irmão
    -0.08
     Yelp
    -0.08
     RGB
    -0.08
    POSITIVE LOGITS
     unconstitutional
    0.14
     legislative
    0.13
     lawmakers
    0.13
     jurisprud
    0.12
     statutes
    0.12
     judiciary
    0.12
     judicial
    0.12
     संसद
    0.12
     promulg
    0.12
     संविधान
    0.12
    Activations Density 0.036%

    No Known Activations