© 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. 19-RESID-POST-AA
    11. 18756
    Prev
    Next
    INDEX
    Explanations

    往

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    েও
    -0.10
    -0.09
     पनि
    -0.09
    ξης
    -0.09
     רק
    -0.09
     דווקא
    -0.09
     edhe
    -0.09
     hefyd
    -0.08
     tamén
    -0.08
     گیرد
    -0.08
    POSITIVE LOGITS
    رام
    0.10
    rie
    0.09
    IE
    0.09
    RAM
    0.09
    OSI
    0.09
    past
    0.08
    roc
    0.08
    urch
    0.08
    ROLL
    0.08
    arc
    0.08
    Activations Density 0.002%

    No Known Activations