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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 96363
    Prev
    Next
    INDEX
    Explanations

    say "9 or 13"

    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
    ема
    -0.09
     Emails
    -0.09
     adopter
    -0.09
     toolkit
    -0.09
     Sending
    -0.08
     Pharmaceutical
    -0.08
    .AG
    -0.08
     التغ
    -0.08
    Emails
    -0.08
     Como
    -0.08
    POSITIVE LOGITS
    عية
    0.08
    [V
    0.08
     piir
    0.07
    ROT
    0.07
    0.07
    .d
    0.07
    0.07
    Matt
    0.07
    40
    0.07
    cry
    0.07
    Activations Density 0.001%
    No Known Activations