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. 75086
    Prev
    Next
    INDEX
    Explanations

    code, file input/output

    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
     Gartner
    -0.09
     contenders
    -0.09
    万美元
    -0.08
     الو
    -0.08
     ransomware
    -0.08
     ning
    -0.08
     kidn
    -0.07
     Serv
    -0.07
     boto
    -0.07
     воспри
    -0.07
    POSITIVE LOGITS
    .flush
    0.11
    .writerow
    0.10
    .write
    0.10
    .Write
    0.10
    .Flush
    0.09
     pause
    0.08
     sebanyak
    0.08
    pause
    0.08
     paused
    0.08
     flush
    0.08
    Activations Density 0.005%

    No Known Activations