© 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. 11-RESID-POST-AA
    11. 26274
    Prev
    Next
    INDEX
    Explanations

    X-Forwarded-For headers

    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
     Morse
    -0.10
     cottage
    -0.09
    ellite
    -0.08
     chant
    -0.08
    ண்டு
    -0.08
    mba
    -0.07
    ண்டும்
    -0.07
     pertence
    -0.07
     rehearsal
    -0.07
    cannot
    -0.07
    POSITIVE LOGITS
    Trusted
    0.10
     trusting
    0.09
     trustworthy
    0.09
     forwarded
    0.09
    可信
    0.09
     bewust
    0.08
    াগত
    0.08
     trusted
    0.08
     spoof
    0.08
     betrouwbare
    0.08
    Activations Density 0.002%

    No Known Activations