© 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. 49983
    Prev
    Next
    INDEX
    Explanations

    Long miscellaneous texts

    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
    ि
    -0.08
     Estonia
    -0.07
    -conscious
    -0.07
     Definit
    -0.07
     pria
    -0.07
    ume
    -0.07
     Conscious
    -0.07
     Lak
    -0.07
     kare
    -0.07
     Panasonic
    -0.07
    POSITIVE LOGITS
    äischen
    0.09
     enc
    0.08
     Dünya
    0.08
     tempest
    0.07
     exploit
    0.07
    ällen
    0.07
    ్లీ
    0.07
     overw
    0.07
    Á
    0.07
    EN
    0.07
    Activations Density 0.009%

    No Known Activations