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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78174
    Prev
    Next
    INDEX
    Explanations

    quality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     접근
    -0.08
     Romeo
    -0.08
     forgotten
    -0.08
     vacant
    -0.07
     medicine
    -0.07
     அண
    -0.07
     surprisingly
    -0.07
     politics
    -0.07
     barefoot
    -0.07
     ಸೇವ
    -0.07
    POSITIVE LOGITS
     hochwert
    0.10
    -quality
    0.09
     hochwertigen
    0.09
    .High
    0.08
    _IMAGES
    0.08
     Mature
    0.08
     kakov
    0.08
     afbeeldingen
    0.08
     Intens
    0.08
    级
    0.08
    Activations Density 0.011%

    No Known Activations