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. 58968
    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
     Vine
    -0.08
     fum
    -0.08
     rinc
    -0.08
     vent
    -0.08
    -leg
    -0.08
    ivos
    -0.07
    izer
    -0.07
     Vent
    -0.07
    桑
    -0.07
    wag
    -0.07
    POSITIVE LOGITS
    '''↵
    0.08
    աք
    0.08
    مان
    0.08
    ین
    0.08
    мак
    0.07
    ميز
    0.07
     initiating
    0.07
    रिया
    0.07
    ①
    0.07
    काल
    0.07
    Activations Density 0.024%

    No Known Activations