© 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. 11-RESID-POST-AA
    11. 44930
    Prev
    Next
    INDEX
    Explanations

    Numbers and quantity

    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
    ifference
    -0.08
    .shift
    -0.08
    arach
    -0.07
     изменить
    -0.07
    증
    -0.07
    하려
    -0.07
     medida
    -0.07
    	C
    -0.07
    .idea
    -0.07
    .describe
    -0.07
    POSITIVE LOGITS
     tiers
    0.09
    -tier
    0.09
     compartments
    0.09
     kase
    0.08
    -layer
    0.08
     layers
    0.08
     ಬಾರಿ
    0.08
     compartment
    0.08
     detachable
    0.08
    轮
    0.08
    Activations Density 0.081%

    No Known Activations