© 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. 7-RESID-POST-AA
    11. 860
    Prev
    Next
    INDEX
    Explanations

    Mixed document fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مزید
    -0.08
     SEX
    -0.08
     milestones
    -0.08
    ుతోంది
    -0.07
    (K
    -0.07
     زیر
    -0.07
     Kil
    -0.07
     застос
    -0.07
     brz
    -0.07
    cab
    -0.07
    POSITIVE LOGITS
     nond
    0.08
    WM
    0.08
    TYPO
    0.08
    =[]↵
    0.07
     Amen
    0.07
     occupants
    0.07
    ile
    0.07
    gang
    0.07
     tende
    0.07
     alleg
    0.07
    Activations Density 0.000%

    No Known Activations