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. 77487
    Prev
    Next
    INDEX
    Explanations

    Fortunately

    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
     implying
    -0.07
    ాణ
    -0.07
     mere
    -0.07
    ைப்ப
    -0.07
    ਣਾ
    -0.07
     bahkan
    -0.07
    ைப்
    -0.07
    سي
    -0.07
     downright
    -0.07
    ød
    -0.07
    POSITIVE LOGITS
     اینکه
    0.08
     Umsetzung
    0.08
    forth
    0.08
     그는
    0.08
     случая
    0.07
     generous
    0.07
    ]);↵//
    0.07
    _decode
    0.07
     ingrédients
    0.07
    与此同时
    0.07
    Activations Density 0.018%

    No Known Activations