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. 102897
    Prev
    Next
    INDEX
    Explanations

    Originally

    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
     ejus
    -0.08
     kidd
    -0.08
     fi
    -0.08
    →
    -0.08
     inj
    -0.08
     Aal
    -0.08
    uera
    -0.08
     iwwer
    -0.08
    alach
    -0.08
     vun
    -0.07
    POSITIVE LOGITS
    "$
    0.07
    "<?
    0.07
    ));
    0.07
     درد
    0.07
    ):
    0.07
     {
    
    ↵
    0.07
     commonplace
    0.07
    "log
    0.07
    {{
    0.07
    configuration
    0.07
    Activations Density 0.069%

    No Known Activations