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. 90186
    Prev
    Next
    INDEX
    Explanations

    optimization algorithms

    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
     borg
    -0.09
    ojen
    -0.09
    मुख
    -0.09
    �
    -0.08
    weddol
    -0.08
     hob
    -0.08
    .hk
    -0.08
    θυ
    -0.08
    @click
    -0.08
    ╝
    -0.08
    POSITIVE LOGITS
    .priority
    0.08
     rankings
    0.08
    encha
    0.07
    ancas
    0.07
     aner
    0.07
    .rank
    0.07
     compliments
    0.07
     ranking
    0.07
    Rank
    0.07
    順位
    0.07
    Activations Density 0.001%

    No Known Activations