© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49748
    Prev
    Next
    INDEX
    Explanations

    per

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     стак
    -0.09
     ы
    -0.09
    ুয়ারি
    -0.08
     auteur
    -0.08
    ويب
    -0.08
    ৃ
    -0.08
     წყ
    -0.08
     চোখ
    -0.08
     қою
    -0.08
     '\''
    -0.08
    POSITIVE LOGITS
     perimeter
    0.19
    imeters
    0.18
     circumference
    0.18
    imeter
    0.15
     perí
    0.13
    围
    0.13
    囲
    0.13
     circum
    0.12
     Circ
    0.12
    circ
    0.11
    Activations Density 0.013%

    No Known Activations