© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 47900
    Prev
    Next
    INDEX
    Explanations

    A

    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
     Ана
    -0.09
     palvel
    -0.09
     tjen
    -0.09
    Anna
    -0.08
     tjän
    -0.08
    ohnt
    -0.08
     Anna
    -0.08
    УЛ
    -0.08
     самом
    -0.08
     �
    -0.08
    POSITIVE LOGITS
    arya
    0.10
    ary
    0.10
    aries
    0.10
    diti
    0.09
    isha
    0.09
    ry
    0.09
    ṣ
    0.09
    yesha
    0.09
    nees
    0.09
    fiya
    0.09
    Activations Density 0.001%

    No Known Activations