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. 44820
    Prev
    Next
    INDEX
    Explanations

    seconds

    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
     parano
    -0.09
    。
    -0.09
    	p
    -0.09
     norte
    -0.09
    。这
    -0.09
    。↵↵
    -0.08
     estet
    -0.08
    。↵
    -0.08
     dzie
    -0.08
     serotonin
    -0.08
    POSITIVE LOGITS
    _CLOCK
    0.08
     clock
    0.08
    clock
    0.08
     Countdown
    0.08
    _clock
    0.07
     Bw
    0.07
    Clock
    0.07
    Opponent
    0.07
    �
    0.07
     tricks
    0.07
    Activations Density 0.007%

    No Known Activations