© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 6114
    Prev
    Next
    INDEX
    Explanations

    say "ise" ending

    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
    ants
    -0.08
    .Ver
    -0.08
    -0.08
    abets
    -0.07
    "ש
    -0.07
    	input
    -0.07
     aangegeven
    -0.07
    aser
    -0.07
     aba
    -0.07
    াধিক
    -0.07
    POSITIVE LOGITS
    isen
    0.09
    ucht
    0.08
    graph
    0.08
     Mickey
    0.08
     recordó
    0.08
    alur
    0.07
    isere
    0.07
    iser
    0.07
     Nakam
    0.07
     recuer
    0.07
    Activations Density 0.000%

    No Known Activations