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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 114081
    Prev
    Next
    INDEX
    Explanations

    ist

    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
     building
    -0.09
    ుతుంది
    -0.09
     оператор
    -0.08
     boolean
    -0.08
     thunk
    -0.08
     constructor
    -0.08
     Container
    -0.08
    Composable
    -0.08
     textual
    -0.08
    Building
    -0.08
    POSITIVE LOGITS
     aspirin
    0.09
    导致
    0.08
     sufferers
    0.08
     dermat
    0.08
    isp
    0.08
    鼻
    0.08
     salmon
    0.08
    ?page
    0.08
     HPV
    0.08
     ವೈದ್ಯ
    0.08
    Activations Density 0.005%

    No Known Activations