© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5851
    Prev
    Next
    INDEX
    Explanations

    -

    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
    ismi
    -0.09
     apolog
    -0.09
     xim
    -0.09
    *K
    -0.08
     beled
    -0.08
     kynt
    -0.08
     schoonheid
    -0.08
     Thom
    -0.08
     pedra
    -0.08
     kualitas
    -0.08
    POSITIVE LOGITS
     uber
    0.08
    Mods
    0.08
     UC
    0.08
    GC
    0.08
    Uber
    0.08
    modus
    0.08
    usid
    0.07
    :+
    0.07
    CAT
    0.07
    Intent
    0.07
    Activations Density 0.001%

    No Known Activations