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. 76499
    Prev
    Next
    INDEX
    Explanations

    Guides and suggestions

    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
     Edo
    -0.08
    AZY
    -0.08
    IRIT
    -0.07
     disproportionately
    -0.07
     fik
    -0.07
     pouze
    -0.07
     jammer
    -0.07
     gait
    -0.07
     defe
    -0.07
     triv
    -0.07
    POSITIVE LOGITS
     nhé
    0.10
     şöyle
    0.09
    👇
    0.09
    ):
    ↵
    ↵
    0.09
    如下
    0.09
    。不过
    0.09
    :
    ↵
    ↵
    0.08
    
    0.08
    :↵↵
    0.08
    

    0.08
    Activations Density 0.121%

    No Known Activations