© 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. 48520
    Prev
    Next
    INDEX
    Explanations

    code sections

    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
     sk
    -0.08
    ე
    -0.08
     impede
    -0.08
    .SK
    -0.08
     demonstra
    -0.08
    Sk
    -0.08
    -grow
    -0.08
     স্ক
    -0.08
     Invoke
    -0.07
     સ્ક
    -0.07
    POSITIVE LOGITS
    رق
    0.09
     të
    0.07
     बताते
    0.07
    cuits
    0.07
     aligned
    0.07
    rekk
    0.07
     used
    0.07
     especiais
    0.07
     Conde
    0.07
    .vector
    0.07
    Activations Density 0.000%

    No Known Activations