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. 12628
    Prev
    Next
    INDEX
    Explanations

    prototype

    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
     ur
    -0.08
     Quan
    -0.08
    ixin
    -0.08
    Bank
    -0.08
     pancreatic
    -0.07
     Vigil
    -0.07
    igal
    -0.07
     Stainless
    -0.07
    vali
    -0.07
    uris
    -0.07
    POSITIVE LOGITS
     purposes
    0.12
     exploratory
    0.12
     doeleinden
    0.11
    /debug
    0.10
     debugging
    0.10
     공부
    0.09
    	debug
    0.09
     prototypes
    0.09
     हेत
    0.09
    用途
    0.09
    Activations Density 0.036%

    No Known Activations