© 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. 19-RESID-POST-AA
    11. 20077
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    援
    -0.08
    edenken
    -0.08
     olyan
    -0.08
     esimerkiksi
    -0.08
     sätt
    -0.08
     JNICALL
    -0.08
     preocup
    -0.08
     violence
    -0.08
    浓
    -0.08
     paljon
    -0.08
    POSITIVE LOGITS
    The
    0.10
    }:
    0.08
     The
    0.08
    :The
    0.08
    augh
    0.08
    Mega
    0.08
    Related
    0.07
    Numberish
    0.07
    rece
    0.07
     Derfor
    0.07
    Activations Density 0.000%

    No Known Activations