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. 58927
    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
     Contains
    -0.09
     Push
    -0.08
    pick
    -0.07
    Hp
    -0.07
     swim
    -0.07
     Starts
    -0.07
    Añ
    -0.07
     Swim
    -0.07
    Push
    -0.07
     picks
    -0.07
    POSITIVE LOGITS
    ரி
    0.09
    ারি
    0.08
     què
    0.08
     finally
    0.08
    gebung
    0.08
     наконец
    0.08
     pleasure
    0.07
     praxis
    0.07
    316
    0.07
    ğu
    0.07
    Activations Density 0.116%

    No Known Activations