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. 78723
    Prev
    Next
    INDEX
    Explanations

    of

    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
     cadenas
    -0.08
     Shaw
    -0.08
    		      
    -0.08
     problém
    -0.07
     rash
    -0.07
     acad
    -0.07
     mascar
    -0.07
     ICollection
    -0.07
     Lets
    -0.07
     sockaddr
    -0.07
    POSITIVE LOGITS
    I'm
    0.08
     deliberately
    0.08
    ânt
    0.08
     berücksicht
    0.08
     intentionally
    0.08
    אני
    0.07
    emuva
    0.07
     weisen
    0.07
     gweld
    0.07
     deliberate
    0.07
    Activations Density 0.000%

    No Known Activations