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. 53197
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Datatype
    -0.08
    _info
    -0.08
    Stan
    -0.07
    -resolution
    -0.07
    (pro
    -0.07
    		  
    -0.07
    _install
    -0.07
    之一
    -0.07
    				  
    -0.07
    많
    -0.07
    POSITIVE LOGITS
     dough
    0.09
     buzz
    0.08
    ory
    0.08
     Buzz
    0.07
     aarde
    0.07
    door
    0.07
     killers
    0.07
     peninsula
    0.07
     weekend
    0.07
    llo
    0.07
    Activations Density 0.050%

    No Known Activations