Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 75354
    Prev
    Next
    INDEX
    Explanations

    removing

    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
     calam
    -0.08
     Dame
    -0.08
     właśnie
    -0.07
     demanded
    -0.07
     HIS
    -0.07
     Urbana
    -0.07
     demand
    -0.07
     newsp
    -0.07
     operate
    -0.07
     behoren
    -0.07
    POSITIVE LOGITS
     potentially
    0.10
     möglicherweise
    0.09
     потенциаль
    0.09
     eventuell
    0.09
     Potential
    0.09
    -Free
    0.09
    无法
    0.09
    风险
    0.09
     You'll
    0.08
    所有
    0.08
    Activations Density 0.030%

    No Known Activations