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. 12702
    Prev
    Next
    INDEX
    Explanations

    question

    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
    ARC
    -0.08
     अवसर
    -0.08
     التق
    -0.08
    łą
    -0.08
     opportunities
    -0.07
     surgical
    -0.07
    ariki
    -0.07
    aper
    -0.07
     فرصت
    -0.07
    ålet
    -0.07
    POSITIVE LOGITS
    size
    0.08
     clich
    0.08
     Alltag
    0.07
    	size
    0.07
     cade
    0.07
     handy
    0.07
     Troubles
    0.07
     troubleshoot
    0.07
     хүс
    0.07
     захот
    0.07
    Activations Density 0.006%

    No Known Activations