© 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. 48642
    Prev
    Next
    INDEX
    Explanations

    definitions

    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
    .encode
    -0.09
    encode
    -0.08
     uncle
    -0.08
    Encoder
    -0.08
    encoder
    -0.08
    encoded
    -0.08
    sem
    -0.08
    Amb
    -0.08
    Adapter
    -0.08
    dro
    -0.08
    POSITIVE LOGITS
     Definition
    0.10
     Rom
    0.10
     définition
    0.10
     PART
    0.10
     Parts
    0.10
     Stroke
    0.10
     Erklärung
    0.10
     definition
    0.09
     Explanation
    0.09
     pronunciation
    0.09
    Activations Density 0.016%

    No Known Activations