© 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. 3-RESID-POST-AA
    11. 12821
    Prev
    Next
    INDEX
    Explanations

    Template

    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
     ever
    -0.08
     IKEA
    -0.07
    nti
    -0.07
     Immer
    -0.07
     IDisposable
    -0.07
    区
    -0.07
     lighthouse
    -0.07
     Faucet
    -0.07
     championships
    -0.07
     affine
    -0.07
    POSITIVE LOGITS
     seroton
    0.09
     음
    0.08
     trif
    0.08
     ses
    0.08
     matin
    0.07
    -q
    0.07
    _q
    0.07
    <Job
    0.07
     sext
    0.07
     rhes
    0.07
    Activations Density 0.000%

    No Known Activations