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. 59169
    Prev
    Next
    INDEX
    Explanations

    stop words

    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
     primi
    -0.08
     chewy
    -0.08
     UINavigation
    -0.07
    Таким
    -0.07
     покуп
    -0.07
    _usec
    -0.07
     comprehensive
    -0.07
     Ainsi
    -0.07
    	
    -0.07
    青青
    -0.07
    POSITIVE LOGITS
     toneladas
    0.11
     milhares
    0.10
     dezenas
    0.10
     centenas
    0.10
     લાખ
    0.10
     milliers
    0.10
     규모
    0.10
    ระดับ
    0.10
     लाख
    0.10
     centaines
    0.10
    Activations Density 0.009%

    No Known Activations