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. 3-RESID-POST-AA
    6. 2311
    Prev
    Next
    INDEX
    Explanations

    variable names / codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ®
    -0.09
    -lock
    -0.08
     בא
    -0.08
    GG
    -0.07
    Agg
    -0.07
     escalation
    -0.07
     Cer
    -0.07
     AAA
    -0.07
     Storm
    -0.07
    Miner
    -0.07
    POSITIVE LOGITS
     Những
    0.08
     Nelson
    0.07
     iho
    0.07
     విక
    0.07
     illuminated
    0.07
     Koh
    0.07
     Sacred
    0.07
    穴
    0.07
    ↵//↵//
    0.07
    .mob
    0.07
    Activations Density 0.000%

    No Known Activations