© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129327
    Prev
    Next
    INDEX
    Explanations

    |

    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
     déf
    -0.08
     Forbes
    -0.08
    /TR
    -0.08
    .MOD
    -0.08
    -0.08
    699
    -0.08
     Rico
    -0.07
    tant
    -0.07
     muscle
    -0.07
     plato
    -0.07
    POSITIVE LOGITS
    0.08
     ensure
    0.07
    itsu
    0.07
     enable
    0.07
    �
    0.07
     вызывает
    0.07
    ै
    0.07
     nerd
    0.07
     fra
    0.07
     conc
    0.07
    Activations Density 0.021%

    No Known Activations