© 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. 49547
    Prev
    Next
    INDEX
    Explanations

    Cyrillic characters

    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
    lico
    -0.08
     Partnerships
    -0.08
     Album
    -0.08
    웃
    -0.08
     seminal
    -0.08
    oug
    -0.08
    haald
    -0.08
     Berufs
    -0.08
     Netzwerk
    -0.08
    ouve
    -0.07
    POSITIVE LOGITS
    yr
    0.12
    jk
    0.12
    JK
    0.09
    mn
    0.09
    unei
    0.09
    une
    0.09
    irth
    0.09
    kl
    0.08
    ahr
    0.08
     mun
    0.08
    Activations Density 0.006%

    No Known Activations