© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 5939
    Prev
    Next
    INDEX
    Explanations

    Pre

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     previo
    -0.08
    comm
    -0.08
    .K
    -0.08
    前
    -0.07
     crumb
    -0.07
     constitu
    -0.07
     karo
    -0.07
     proactively
    -0.07
     COMM
    -0.07
     Corpus
    -0.07
    POSITIVE LOGITS
    Ampl
    0.10
    am
    0.09
     amplifier
    0.09
    amp
    0.09
     Ampl
    0.09
    irr
    0.08
     amplification
    0.08
     pilers
    0.08
    strained
    0.08
    ampion
    0.08
    Activations Density 0.006%

    No Known Activations