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. 213
    Prev
    Next
    INDEX
    Explanations

    parts or measurements

    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
    	cc
    -0.09
    cc
    -0.08
    (cc
    -0.07
     cc
    -0.07
    	p
    -0.07
     especificamente
    -0.07
     accelerate
    -0.07
     específicamente
    -0.07
     вый
    -0.07
    ≫
    -0.07
    POSITIVE LOGITS
    都
    0.14
     imaginable
    0.14
    都有
    0.14
     وكل
    0.12
     behalve
    0.11
     eneste
    0.11
    都是
    0.11
     nook
    0.11
     Every
    0.11
     đều
    0.10
    Activations Density 0.119%

    No Known Activations